CN113723369A

CN113723369A - Control method, control device, electronic equipment and storage medium

Info

Publication number: CN113723369A
Application number: CN202111279235.5A
Authority: CN
Inventors: 黄燕青; 汪紫超; 杨海波; 阎超
Original assignee: Shanghai Chuangmi Technology Co ltd; Beijing Chuangmizhihui Iot Technology Co ltd
Current assignee: Shanghai Imilab Technology Co Ltd
Priority date: 2021-11-01
Filing date: 2021-11-01
Publication date: 2021-11-30
Anticipated expiration: 2041-11-01
Also published as: CN113723369B

Abstract

The disclosure provides a control method, a control device, an electronic device and a storage medium. The method comprises the following steps: step 101: the processor controls the main camera to acquire images in real time; step 102: the processor judges whether the main camera is in a shielding state or not based on the current image acquired in real time, if so, the step 103 is executed, and if not, the step 105 is executed; step 103: the processor generates voice warning information and sends the voice warning information through the audio component; step 104: the processor acquires an image containing a target human body shot by the auxiliary camera in real time, and returns to execute the step 102; step 105: the processor determines the light emitting direction of the white light lamp and the target shooting direction and the target focal length of the main camera based on the position of the face of the target human body, controls to turn on the white light lamp, and controls the main camera to shoot an image containing the face of the target human body.

Description

Control method, control device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of information processing technologies, and in particular, to a control method and apparatus, an electronic device, and a storage medium.

Background

In the related art, smart cats with functions of photographing, image recognition, and the like are increasingly used by users. However, especially during the night time when the user is resting, dangerous persons present outdoors may not be timely and accurately found due to environmental influences. Therefore, how to effectively and timely identify the people who have security threats and exist outside the house of the user through the intelligent cat eye, and then the safety of the user in the house is ensured to be the problem to be solved.

Disclosure of Invention

The present disclosure provides a control method, an apparatus, an electronic device, and a storage medium to solve the above technical problems.

In a first aspect, the present disclosure provides a control method, the method comprising:

step 101: the method comprises the steps that a processor of the intelligent cat eye controls a main camera of the intelligent cat eye to acquire images in real time under the condition that the processor of the intelligent cat eye detects that a first distance between a target human body and the intelligent cat eye is smaller than a first preset distance threshold value based on an infrared sensor of the intelligent cat eye, and a second distance between the face of the target human body and the intelligent cat eye is smaller than a second preset distance threshold value based on a laser radar of the intelligent cat eye;

step 102: the processor of the intelligent cat eye judges whether the main camera is in a shielding state or not based on the current image acquired by the main camera in real time, and if the main camera is in the shielding state, the step 103 is executed; if not, go to step 105;

step 103: the processor of the intelligent cat eye generates voice warning information, and the voice warning information is sent out through an audio component of the intelligent cat eye; the voice warning information is used for reminding the target human body to remove the shielding object;

step 104: the processor of the intelligent cat eye starts an auxiliary camera of the intelligent cat eye and obtains an image which is obtained by the auxiliary camera in real time and contains the target human body, and the step 102 is executed; the auxiliary camera and the main camera are arranged at different positions on the intelligent cat eye;

step 105: the processor of the intelligent cat eye determines the light emitting direction of the white light lamp and determines the target shooting direction and the target focal length of the main camera based on the position of the face of the target human body, the processor of the intelligent cat eye controls the white light lamp to be turned on so that the white light lamp emits white light to the light emitting direction, and controls the main camera of the intelligent cat eye to adjust to the target focal length so as to shoot an image containing the face of the target human body in the target shooting direction.

In a second aspect, the present disclosure provides a control apparatus, the apparatus comprising:

the processor is used for controlling the main camera to acquire images in real time under the condition that the infrared sensor based on the intelligent cat eye detects that a first distance between a target human body and the intelligent cat eye is smaller than a first preset distance threshold value and the laser radar based on the intelligent cat eye detects that a second distance between the face of the target human body and the intelligent cat eye is smaller than a second preset distance threshold value; judging whether the main camera is in a shielding state or not based on a current image acquired by the main camera in real time, if so, generating voice warning information, and sending the voice warning information through an audio component, wherein the voice warning information is used for reminding the target human body to move away from a shielding object, starting an auxiliary camera and acquiring an image containing the target human body, which is obtained by the auxiliary camera through real-time shooting, and the auxiliary camera and the main camera are arranged at different positions on the smart cat eye; if the human body is not in the shielding state, based on the position of the face of the target human body, determining the light-emitting direction of a white light lamp, determining the target shooting direction and the target focal length of the main camera, controlling to turn on the white light lamp to enable the white light lamp to emit white light to the light-emitting direction, and controlling the main camera to adjust to the target focal length to shoot an image containing the face of the target human body in the target shooting direction;

the infrared sensor is used for detecting a first distance between a target human body and the intelligent cat eye;

the laser radar is used for detecting a second distance between the face of the target human body and the intelligent cat eye;

the main camera is used for acquiring images in real time;

the auxiliary camera is used for starting and shooting images containing the target human body based on the control of the processor;

a white light lamp for emitting white light to the light emitting direction based on the control of the processor;

and the audio component is used for giving out voice warning information.

In a third aspect, the present disclosure provides an electronic device, comprising:

one or more processors;

a memory communicatively coupled to the one or more processors;

one or more computer programs, wherein the one or more computer programs are stored in the memory, which when executed by the electronic device, cause the electronic device to perform the method provided by the first aspect above.

In a fourth aspect, the present disclosure provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the method provided by the first aspect.

The technical scheme provided by the disclosure at least comprises the following beneficial effects:

under the condition that the distance between a target human body and the intelligent cat eye is smaller than a first preset distance threshold value in a detection area of an infrared sensor on the intelligent cat eye, and the distance between the face of the target human body and the intelligent cat eye is smaller than a second preset distance threshold value through laser radar, whether the main camera is blocked or not can be analyzed through a current image collected by the main camera in real time, under the condition that the main camera is blocked, the target human body is warned through voice warning information, and an auxiliary camera is started to shoot the target human body; and under the condition that the main camera is not shielded, the white light lamp can be controlled to emit light towards the face of the target human body and the main camera is controlled to shoot the target human body. Therefore, the outdoor target human body can be timely and accurately identified and found by adopting the scheme, so that the warning and the deterrence are carried out under the condition that the distance between the target human body and the intelligent cat eye is too short, and the safety of the user in the room is ensured.

Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

Fig. 1 is a first flowchart illustrating a control method of a smart cat eye according to an embodiment of the present disclosure;

FIG. 2 is a second flowchart illustrating a method for controlling a smart cat eye according to an embodiment of the present disclosure;

FIG. 3 is a third schematic flowchart of a method for controlling a smart cat eye according to another embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a camera coordinate system and a world coordinate system provided by another embodiment of the present disclosure;

fig. 5 is a schematic processing flow diagram of prediction of a movement trajectory of a target human body according to another embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a structure of a smart cat eye according to another embodiment of the present disclosure;

FIG. 7 is a block diagram of an electronic device for implementing a method of controlling a smart cat eye according to an embodiment of the present disclosure.

Detailed Description

The present disclosure will be described in further detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, circuits, etc., that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.

In the related art, a user may install a smart cat eye to observe a person or thing appearing outdoors to determine whether to let the person outdoors enter indoors. However, users often cannot observe people who may have security threats to themselves in real time, and especially cannot timely and accurately find dangerous people who appear outdoors in a rest time period of the users at night. Therefore, how to effectively and timely identify people with security threats through the intelligent cat eye and further ensure the security of the user to be the problem to be solved.

In view of the foregoing problems, embodiments of the present disclosure provide a control method, and processing logic implementing the method may be deployed in a smart cat eye. As shown in fig. 1, a control method according to an embodiment of the present disclosure includes:

step 105: the processor of the intelligent cat eye determines the light emitting direction of the white light lamp and determines the target shooting direction and the target focal length of the main camera based on the position of the face of the target human body, the processor of the intelligent cat eye controls to open the white light lamp so that the white light lamp emits white light to the light emitting direction, and controls the main camera of the intelligent cat eye to adjust to the target shooting direction to shoot an image containing the face of the target human body with the target focal length.

The method provided by the embodiment of the disclosure can be particularly suitable for being used in a preset time period, which can specifically refer to night, such as after 6 pm (i.e., 18: 00-24: 00) and before 6 am (i.e., 0: 00-6: 00); of course, the preset time period may also be set according to actual situations, and all possible situations are not exhaustive. Accordingly, before performing step 101, the method may further include: and the processor of the intelligent cat eye judges whether the current moment is in the preset time period, if so, the step 101 is executed, and if not, the processor continuously judges whether the current moment is in the preset time period.

Before the step 101 is executed, the processor of the smart cat eye further determines whether the target human body is detected according to a current detection result obtained by detecting a human body in real time by an infrared sensor installed in the processor, and determines whether a first distance between the target human body and the smart cat eye is smaller than a first preset distance threshold, specifically as shown in fig. 2, the method may include:

step 201: the method comprises the steps that an infrared sensor of an intelligent cat eye detects a human body in real time to obtain a current detection result, a processor of the intelligent cat eye judges whether a target human body exists in a detection range of the infrared sensor or not based on the current detection result, and if yes, step 202 is executed; if not, continue to execute step 201;

step 202: the processor of the intelligent cat eye determines a first distance between the target human body and the intelligent cat eye based on the current detection result, judges whether the first distance is smaller than a first preset distance threshold value, and if the first distance is smaller than the first preset distance threshold value, acquires an image containing the target human body through a main camera of the intelligent cat eye; otherwise, return to execute step 201.

Wherein, in step 201, the infrared sensor of intelligence cat eye carries out human body detection in real time and obtains current detection result, specifically can refer to: the processor of the intelligent cat eye controls the infrared sensor to start real-time detection; the infrared sensor of the intelligent cat eye detects the human body in real time in the detection range covered by the infrared sensor to obtain the current detection result.

The detection range covered by the infrared sensor of the smart cat eye may be related to the performance of the infrared sensor itself, preset distance measurement parameters, and other configurations, for example, the detection range of the infrared sensor may be 0 to 50 meters, or 0 to 100 meters, or 0 to 20 meters, and the like, which is not limited herein.

The infrared sensor can be composed of an infrared transmitting circuit, an infrared receiving circuit and the like. The infrared transmitting circuit is used for emitting infrared light (for example, infrared light with a frequency of 40 kHz), and the infrared receiving circuit is used for receiving a reflected wave signal of the infrared light and converting the reflected wave signal into an electric signal. It should also be understood that the emission of infrared light by the infrared emission circuit may be periodic, such as emitting infrared light every 0.1 second, although the period may be greater or smaller, and is not limited herein.

The current detection result may include: detecting a target human body and a first distance between the target human body and a smart cat eye; alternatively, the target human body is not detected.

The target human body may refer to any one of human bodies located within a detection range of the infrared sensor; in addition, one or more human bodies can be detected within the detection range of the infrared sensor, in this embodiment, any one of the one or more human bodies detected by the infrared sensor is referred to as a target human body for subsequent description, and it should be noted that, when a plurality of human bodies are detected by the current infrared sensor, the subsequent processing of this embodiment may be performed for each human body as the target human body respectively for a plurality of times in sequence.

In step 202, the processor of the smart cat eye determines a first distance between the target human body and the smart cat eye based on the current detection result, which may refer to: and the processor of the intelligent cat eye acquires a first distance between the target human body and the intelligent cat eye from the current detection result.

As already described above, the current detection result may include the detected target human body and the first distance between the target human body and the smart cat eye, that is, in a case that the target human body is detected, the first distance between the target human body and the smart cat eye may be directly obtained.

Further, the infrared receiving circuit in the aforementioned infrared sensor may be configured to receive a reflected wave signal of the infrared light and convert the reflected wave signal into an electrical signal, and accordingly, a first distance s1 between the target human body and the smart cat eye may be calculated by calculating a time difference t between the infrared ray emitted by the infrared emitting circuit and the reflected wave received by the infrared receiving circuit, for example, the first distance may be calculated by s1= (c × t)/2; wherein s1 represents a first distance between the target human body and the smart cat eye, t represents a time difference between the infrared ray emitted by the infrared emitting circuit and the reflected wave received by the infrared receiving circuit, c represents an optical speed, and c generally takes a value of 3 × 108 m/s.

The first preset distance threshold may be set according to an actual situation, and it should be understood that the first preset distance threshold is smaller than a maximum distance of a detectable range of the infrared sensor. For example, the maximum distance of the detectable range of the infrared sensor is 100 meters, the first preset distance threshold is less than 100 meters, and may be 50 meters or 10 meters, and so on, which are not limited herein.

In step 202, the image containing the target human body is collected in real time through the main camera of the smart cat eye, which specifically can be: the processor of intelligence cat eye controls and starts the main camera of intelligence cat eye self, in order to control the main camera of intelligence cat eye begins to gather in real time and contains the image of target human body.

Here, it should be noted that this embodiment is particularly applicable to nighttime, and correspondingly, when the main camera of the smart cat eye is controlled to start to collect the image including the target human body, the infrared light supplement lamp of the smart cat eye may also be controlled to be turned on, so that the main camera of the smart cat eye collects a clear image including the target human body when the infrared light supplement lamp is turned on; or, the infrared light supplement lamp of the smart cat eye may be controlled to be turned on in step 201, and when the processing in step 202 is executed, the main camera of the smart cat eye acquires a clear image including the target human body under the condition that the infrared light supplement lamp is turned on.

After the processing of steps 201 to 202 is completed, the scheme provided in this embodiment may further control to start the laser radar to perform secondary ranging on the target human body, so as to determine whether to trigger execution of step 101 based on a second distance acquired by the laser radar, which is specifically shown in fig. 3, and may include:

step 301: the processor of the intelligent cat eye identifies the face in the current image of the target human body, which is acquired and contained by the main camera of the intelligent cat eye, so as to judge whether the target human body is an identity allowing the target human body to enter the room, and if not, the step 302 is executed; if so, controlling a communication component of the intelligent cat eye to send prompt information to prompt a user to execute subsequent processing;

step 302: the processor of the smart cat eye determines the current relative position of the face of the target human body based on the current image containing the target human body, and determines the target orientation of the laser radar based on the current relative position of the face of the target human body and the position of the laser radar of the smart cat eye;

step 303: the processor of the intelligent cat eye controls the laser radar to perform distance acquisition under the orientation of the target so as to obtain a second distance between the face of the target human body and the intelligent cat eye;

step 304: the processor of the smart cat eye judges whether the second distance is smaller than the second preset distance threshold value, if not, the step 302 is executed again; if so, go to step 101.

The main camera of the smart cat eye in the step 301 collects the current image including the target human body, and may collect the current image collected at the current time in the image including the target human body in real time for the main camera of the smart cat eye in the step 202.

Specifically, the step 301 of identifying, by the processor of the smart cat eye, the face in the current image containing the target human body collected by the main camera of the smart cat eye to determine whether the target human body is an identity allowing to enter the room may be:

the processor of the intelligent cat eye inputs the current image which is acquired by the main camera of the intelligent cat eye and contains the target human body into a face detection model to obtain the position information of a face area which is output by the face detection model and contains the face;

the processor of the intelligent cat eye extracts a face image from a current image containing the target human body based on the position information of the face region;

the processor of the intelligent cat eye inputs the face image into a face recognition model to obtain the image similarity between the face image and a reference face image; the face image recognition model is a deep neural network model for face recognition, which is obtained by training a plurality of sample face images; the reference face image is a face image of a person allowed to enter a room and preset in the face image recognition module;

the processor of the intelligent cat eye judges whether the image similarity between the face image and the reference face image is greater than a preset similarity threshold value, and if so, the target human body is determined to be an identity allowing the target human body to enter the room; otherwise, determining the target human body as an identity which is not allowed to enter the room.

The face detection model is used for detecting whether a face is contained or not or whether a face region is contained or not from an input image, the output result of the face detection model can be a probability value of the face region contained in the input image, and only under the condition that the probability value is greater than a preset probability threshold value, the output result of the face detection model also contains the position information of the face region of the face.

That is to say, the face detection model is used to detect a probability value of a face (or a face region) included in an input image, and when the probability value is higher than a preset probability threshold value, the face detection model also outputs position information of the face region including the face in the image.

The position information may include a lower left position coordinate and an upper right position coordinate of the face region; alternatively, the position information may include position coordinates of a center point of the face region, and length and width information, etc.

The preset probability threshold may be set according to practical situations, for example, may be 80%, or may be 90%, or higher or lower, and is not exhaustive here.

The face recognition model is used for recognizing the face in the face image to obtain the recognition result of whether the face in the face image is the identity allowed to enter the room or not. The recognition result may be a result of two classifications, such as face recognition model output: the target human body corresponding to the face is an identity which is allowed to enter the room, or the target human body corresponding to the face is an identity which is not allowed to enter the room; or, the identification result may further include identity information corresponding to the human face, in a case where the target human body corresponding to the human face is an identity that allows entering the room. The identity information may be at least one of a name, an identifier, and a number of a face of the target human body.

The similarity threshold may be set according to practical situations, for example, may be 95%, or may be higher or lower, and is not limited herein.

It should be noted that, the above-mentioned processing of the processor of the smart cat eye collecting the current image including the target human body by the main camera of the smart cat eye and inputting the current image into the face detection model, and obtaining the position information of the face region including the face output by the face detection model may further include:

the processor of the intelligent cat eye inputs the current image which is acquired by the main camera of the intelligent cat eye and contains the target human body into a face detection model to obtain an output result of the face detection model;

the processor of the intelligent cat eye judges whether the output result contains the position information of the face region of the face, and if so, the position information of the face region containing the face, which is output by the face detection model, is obtained; if not, then the treater of intelligence cat eye is based on containing the human current image of target is confirmed the adjustment direction and the angle of adjustment of main camera, and the basis adjustment direction and angle of adjustment are right the shooting angle of the main camera of intelligence cat eye adjusts, return the execution the treater of intelligence cat eye will the main camera of intelligence cat eye gathers and contains the human current image input face detection model of target obtains the processing of face detection model's output result.

The processor of the smart cat eye determines the adjustment direction and the adjustment angle of the main camera based on the current image containing the target human body, and specifically may include at least one of the following:

determining that the relative position of the human body is above the middle area of the image based on the current image containing the target human body, and determining that the adjustment direction of the main camera is upward and the adjustment angle is a preset stepping angle; the preset stepping angle may be set according to actual conditions, and may be 1 degree or 5 degrees, for example.

Determining that the relative position of the human body is below the middle area of the image based on the current image containing the target human body, and determining that the adjustment direction of the main camera is downward and the adjustment angle is a preset stepping angle; the preset stepping angle may be set according to actual conditions, and may be 1 degree or 5 degrees, for example.

Determining that the relative position of the human body is the right side of the image based on the current image containing the target human body, and determining that the adjusting direction of the main camera is the right side and the adjusting angle is a preset stepping angle; the preset stepping angle may be set according to actual conditions, and may be 1 degree or 5 degrees, for example.

Determining that the relative position of the human body is the left side of the image based on the current image containing the target human body, and determining that the adjusting direction of the main camera is the left side and the adjusting angle is a preset stepping angle; the preset stepping angle may be set according to actual conditions, and may be 1 degree or 5 degrees, for example.

For example, if it is determined that the human body is located at the upper right of the image, the adjustment direction of the main camera is determined to be rightward and upward, and the adjustment angles corresponding to the two adjustment directions are both preset step angles, for example, 5 degrees are adjusted upward and 5 degrees are also adjusted rightward.

In the above processing manner, a preset step angle is adopted for iterative adjustment, that is, after this adjustment is completed, the main camera of the smart cat eye is returned to collect the current image including the target human body and input the current image into the face detection model again to obtain the output result of the face detection model until the processor of the smart cat eye can process the current image including the target human body to obtain the position information of the face region including the face output by the face detection model, and then the processor of the smart cat eye can be executed to input the face image into the face recognition model to obtain the image similarity between the face image and the reference face image and the subsequent processing of the face image.

In step 301, if it is determined that the target human body is a human body allowed to enter the room, the communication component of the smart cat eye may be controlled to send a prompt message to prompt the user to perform subsequent processing, and then the process returns to step 201 to perform the next processing.

Still further, the control unit of the smart cat eye sends a prompt message to prompt the user to perform subsequent processing, which may include any one of the following:

the processor of the intelligent cat eye generates first prompt information containing the face image; controlling a communication component of the intelligent cat eye to send first prompt information to terminal equipment of a user so as to prompt the user whether to open a door;

the processor of the intelligent cat eye determines the identity information of the target human body based on the face image and generates second prompt information based on the identity information of the target human body; controlling a communication component of the intelligent cat eye to send second prompt information to terminal equipment of a user so as to prompt the user whether to open a door;

the processor of the intelligent cat eye determines the identity information of the target human body based on the face image and generates third prompt information based on the identity information of the target human body; and controlling an audio component of the intelligent cat eye to convert the third prompt information into audio information, and playing the audio information to a user in a room to prompt the user whether to open the door.

The determining, by the processor of the smart cat eye, the identity information of the target human body based on the face image may include: determining a reference face matched with the face image based on a reference face contained in a preset face database and associated preset identity information thereof; and determining the identity information of the target human body based on the preset identity information associated with the reference human face.

After the aforementioned step 301 is completed, step 302 is executed, in which the processor of the smart cat eye determines the current relative position of the face of the target human body based on the current image containing the target human body, and determines the target orientation of the lidar based on the current relative position of the face of the target human body and the position of the lidar of the smart cat eye.

Specifically, the processor of the smart cat eye may determine, based on the current relative position of the face of the target human body in the current image containing the target human body in the camera coordinate system, the position coordinate of the central point of the face of the target human body in the world coordinate system; and determining the target orientation of the laser radar based on the position coordinate of the central point of the face of the target human body in the world coordinate system and the position coordinate of the laser radar in the world coordinate system.

It should be noted that, before the implementation of the present embodiment, a conversion relationship between the camera coordinate system of the main camera and the world coordinate system may be constructed, such as exemplarily described in conjunction with fig. 4:

in fig. 4, point O is the position of the main camera, and Xc, Yc, and Zc are the camera coordinate system (three coordinate axes under the camera coordinate system of the main camera), where Zc may be the coordinate axis of the center of the main camera view angle; o1 is the center of the camera coordinate system (or the center point of a two-dimensional image captured by the main camera in the camera coordinate system (shown as xy-axis in fig. 4)). Ow is the center point of the world coordinate system, and Xw, Yw, Zw are the world coordinate system (or called three coordinate axes under the world coordinate system). The point P is a projection point of the far actual point P (Xc, Yc, Zc) on the image (i.e., a two-dimensional image captured by the main camera). After the main camera acquires the depth of the point P by means of the infrared sensor (or the laser radar), the coordinate value P (Xc, Yc, Zc) of the point P in the camera coordinate system can be calculated based on the internal reference of the main camera and the distance information, and the coordinate (or position coordinate) P (Xw, Yw, Zw) of the point P in the world coordinate system can be obtained by converting the matrix. The conversion relationship between the camera coordinate system and the world coordinate system may be composed of a translation vector (or a translation vector matrix) and a rotation matrix, and the conversion relationship between the camera coordinate system and the world coordinate system of the exemplary P point may be represented by equation 1:

equation 1

Wherein t is a translation vector (or translation vector matrix) of 3 × 1, that is, a vector formed by the position (or position information) of the main camera in a world coordinate system. The translation vector matrix may be a vector of the position information of the main camera in a world coordinate system.

R is a 3 x 3 rotation matrix, which can be derived from the attitude information of the main camera, for example, if the angle of the main camera is rotated by ψ, φ and θ (which can be in a world coordinate system) around the x, y and z axes, respectively, the rotation matrix R = Rx (ψ), Ry (φ), Rz (θ). The specific calculation modes of Rx (ψ), Ry (Φ), Rz (θ) are shown in formulas 2 to 4:

equation 2

Equation 3

Equation 4

Step 303 may then be performed: and the processor of the intelligent cat eye controls the laser radar to carry out distance acquisition under the orientation of the target so as to obtain a second distance between the face of the target human body and the intelligent cat eye.

The method specifically comprises the following steps: the intelligent cat eye starts a laser radar of the intelligent cat eye, controls the laser radar to carry out distance acquisition under the direction of the target, and obtains the current distance between the face of the target human body and the laser radar; and converting the current distance between the face of the target human body and the laser radar into a distance in the horizontal direction to obtain a second distance between the face of the target human body and the intelligent cat eye.

As already described above, the present embodiment pre-constructs the transformation relationship between the camera coordinate system and the world coordinate system, so that when the processing of step 303 is executed, the processor of the smart cat eye can determine the position of the face of the target human body according to the current relative position of the face image in the current image including the target human body and the transformation relationship between the camera coordinate system and the world coordinate system; and the position of the face of the target human body is a coordinate position in the world coordinate system.

Still further, the position of the face of the target human body may specifically be: the coordinate position of the central point of the face of the target human body under a world coordinate system; further alternatively, it may be: the coordinate position of the uppermost point of the face of the target human body in the world coordinate system and the coordinate position of the lowermost point of the face of the target human body in the world coordinate system.

In step 304, the second preset distance threshold is smaller than the first preset distance threshold, for example, the first preset distance threshold is 10 meters, the second preset distance threshold may be 5 meters or 3 meters, and so on, which are not exhaustive here.

After the processing of the foregoing steps 201 to 202 and steps 301 to 304 is completed, if the first distance between the target human body and the smart cat eye is smaller than a first preset distance threshold and the laser radar based on the smart cat eye detects that the second distance between the face of the target human body and the smart cat eye is smaller than a second preset distance threshold, the execution of the foregoing step 101 is triggered.

In the step 101, the processor of the intelligent cat eye controls the main camera of the intelligent cat eye to acquire images in real time and also controls the infrared light supplement lamp of the intelligent cat eye to be turned on, so that the main camera of the intelligent cat eye acquires clear images containing a target human body under the condition that the infrared light supplement lamp is turned on.

In step 102, the processor of the smart cat eye determines whether the main camera is in a shielding state based on the current image acquired by the main camera in real time, and may include:

a processor of the intelligent cat eye detects a current image acquired by the main camera; and if the processor of the intelligent cat eye determines that the current image does not contain the target human body, determining that a main camera of the intelligent cat eye is in a shielding state, and storing the currently acquired image.

It is to be understood that the current image may be an image captured by the main camera at the current time when step 102 is performed.

The determination method that the current image does not contain the target human body may include any one of the following:

the current image does not contain any image, or all pixels in the current image are only a single color (such as black or red or other colors); in this case, usually, the target human body, that is, the stranger (or intruder), intentionally blocks the main camera of the smart cat eye, for example, the main camera of the smart cat eye is blocked by hand, or the main camera of the smart cat eye is blocked by other objects;

the current image comprises images in partial areas and the rest areas do not comprise any images, or all pixels in the rest areas are only in a single color; similarly, this situation may be that the target person, i.e. the stranger (or intruder), intentionally blocks a part of the main camera of the smart cat's eye, for example, the main camera of the smart cat's eye is blocked by hand, or the main camera of the smart cat's eye is blocked by other objects;

a part of image of the target human body is contained in a part of area in the current image, and the rest of area does not contain any image, or all pixels in the rest of area are only in a single color; also, this may often be the case when the target person, i.e. a stranger (or intruder), intentionally obscures a portion of the primary camera of the smart cat's eye, such as by hand or by other items.

In step 103, the processor of the smart cat eye generates voice warning information, and the voice warning information is sent out through an audio component of the smart cat eye; the voice warning information is used for reminding the target human body to remove the shielding object.

Here, the voice warning information may be audio information preset by the user, and the voice warning information may be sounded using any voiceprint, which is not limited herein. The content of the voice warning information may also be a content preset by the user, for example, "it is detected that you block the main camera, please remove the blocking object," or "please not block the main camera," and so on, which are not exhaustive.

In step 104, the auxiliary camera of the smart peephole is installed at a different position from the main camera of the smart peephole, for example, the main camera of the smart peephole is installed at the middle part of the outdoor side of the smart peephole, and of course, according to actual conditions, the auxiliary camera of the smart peephole can also be installed at other positions of the outdoor side of the smart peephole, which is not exhaustive here; the auxiliary camera of the smart cat eye can be preset in the smart cat eye, and the auxiliary camera can be fixed on the moving part and can move along with the movement of the moving part, and when step 104 is executed, the processor of the smart cat eye can control the moving part of the auxiliary camera of the smart cat eye to move the auxiliary camera of the smart cat eye from the inside of the smart cat eye to the outside of the smart cat eye, and specifically can move the auxiliary camera of the smart cat eye from the side (such as the right side, the lower side, the upper side or the left side) of the smart cat eye to the outside of the smart cat eye.

The step 104 may specifically include:

the processor of the intelligent cat eye opens an auxiliary camera of the intelligent cat eye, and the auxiliary camera is moved out from the inside of the intelligent cat eye to the specified side face of the intelligent cat eye to the outside of the intelligent cat eye by controlling a moving part of the auxiliary camera;

the processor of the intelligent cat eye controls the auxiliary camera to shoot at a plurality of angles to obtain images of all the angles at the plurality of angles;

the processor of the intelligent cat eye determines the shooting angle capable of shooting the image containing the target human body according to the images at all the angles;

the processor of the intelligent cat eye controls the auxiliary camera to shoot in real time at a shooting angle containing the image of the target human body to obtain the image containing the target human body.

It should be noted that, while executing the processing of step 103 and step 104, the method may further include:

under the condition that the main camera of the intelligent cat eye is determined to be in a shielding state, the processor of the intelligent cat eye controls to start the static electricity generation component, so that the area where the main camera of the intelligent cat eye is located sends static electricity pulses.

The area where the main camera of the intelligent cat eye is located specifically means the outer surface of the area where the main camera of the intelligent cat eye is located.

It has been described above that the main camera of the smart peephole is in a shielding state, and it may be that a target human body (a stranger or an intruder) maliciously shields the main camera, so that the scheme provided by this embodiment can control sending an electrostatic pulse to the outer surface of the area where the main camera of the smart peephole is located under the condition that it is determined that the main camera of the smart peephole is in the shielding state, so as to initiate an electric shock to the target human body and make it no longer shield the main camera of the smart peephole. Therefore, the target human body, namely a stranger or an invader, is further warned to ensure the safety of indoor personnel, and particularly the safety of indoor personnel at night.

In addition, in this embodiment, a static electricity generating component is disposed in the smart cat eye, and the processor of the smart cat eye can further control the static electricity generating component to send a static electricity pulse to the surfaces of the main camera of the smart cat eye and the auxiliary camera of the smart cat eye at set time intervals (for example, 10 minutes or 1 hour or longer or shorter, which is not exhaustive), so as to remove dust on the surface of the compound eye unit. Therefore, the situation of misjudgment caused by the fact that the main camera or the auxiliary camera is shielded by dust can be avoided, and the judgment accuracy is improved.

That is to say, if it is determined through the foregoing steps 201 to 202 that a target human body (or a stranger or an intruder) exists in the detection area of the infrared sensor, and the distance between the target human body and the smart cat eye is also determined through the laser radar through the processing of the foregoing steps 301 to 304, and then the processing is performed to step 101, it can be analyzed whether the main camera is maliciously blocked by the target human body (or the stranger or the intruder) through the current image acquired by the main camera in real time in step 102, and in the case that the main camera is blocked, the processing of the steps 103 to 104 is performed to warn or frighten the target human body (or the stranger or the intruder). By adopting the scheme, the outdoor target human body can be timely and accurately identified and found, so that warning and deterrence are performed under the condition that the distance between the target human body and the intelligent cat eye is too short and the behavior of shielding the main camera of the intelligent cat eye is possible, and the safety of the user in the room is ensured.

In this embodiment, step 104 and step 103 may be executed simultaneously, or step 104 may be executed first and then step 103 may be executed, or step 103 may be executed first and then step 104 may be executed.

After step 103 and step 104 are completed, the process may return to the loop of step 102 to step 104. In addition, when the processing of steps 102 to 104 is executed in a loop, the method provided by this embodiment may further include:

after the audio component of the intelligent cat eye sends out the target duration of the voice warning information, if the processor of the intelligent cat eye determines that the main camera of the intelligent cat eye is continuously in a shielding state based on the image currently acquired by the main camera of the intelligent cat eye, the processor of the intelligent cat eye obtains a first preset voice and controls the audio component of the intelligent cat eye to send out the first preset voice;

the first preset voice is generated by the voice of a home owner and used for warning that the target human body is far away from a house and warning that the relevant image of the target human body is stored and uploaded to the cloud.

Here, the first preset voice is different from the voice warning information, and the voice warning information is used for prompting a target human body to remove a shielding object; the first preset voice is further used for prompting that the image of the target human body, namely a stranger, is stored and uploaded to the cloud end so as to warn the stranger to leave as soon as possible. In addition, the first preset voice adopts the voice (or voiceprint) of the family owner, so that strangers can mistakenly think that the user himself has found his suspicious behavior, and the deterrence of the strangers is further improved.

If the processor of the smart cat eye determines that the main camera is not in a shielding state based on the current image acquired by the main camera in real time in the previous step 102, executing step 105, wherein the processor of the smart cat eye determines the light-emitting direction of the white light lamp and determines the target shooting direction and the target focal length of the main camera based on the position of the face of the target human body, and controls to turn on the white light lamp so that the white light lamp emits white light in the light-emitting direction and to adjust the main camera of the smart cat eye to the target focal length so as to shoot an image containing the face of the target human body in the target shooting direction, in such a scene, the main camera of the smart cat eye is not shielded, but the possibility that the target human body (stranger or invader) has a safety invasion to people in the scene still cannot be excluded, therefore, the present embodiment alerts the target human body by performing the process of step 105.

Specifically, in step 105, the processor of the smart cat eye determines, based on the position of the face of the target human body, a light emitting direction of the white light lamp and a target shooting direction and a target focal length of the main camera, which may specifically be:

the processor of the intelligent cat eye detects the face image of the target human body based on the current image acquired by the main camera in real time;

determining the coordinate position of the central point of the face of the target human body in a world coordinate system based on the position of the face image in the camera coordinate system and the conversion relation between the camera coordinate system and the world coordinate system;

determining the light emitting direction of a white light lamp based on the coordinate position of the central point of the face of the target human body in a world coordinate system and the coordinate position of the white light lamp of the intelligent cat eye in the world coordinate system; and the processor of the intelligent cat eye is based on the coordinate position of the central point of the face of the target human body in the world coordinate system, the coordinate position of the main camera of the intelligent cat eye in the world coordinate system, the target shooting direction of the main camera and the target focal length.

When the processor of the intelligent cat eye determines the light emitting direction of the white light lamp based on the position of the face of the target human body, the method further comprises the following steps: and the processor of the intelligent cat eye inputs the distance between the face of the target human body and the white light lamp of the intelligent cat eye into a light field determination model, and determines the current light field of the white light lamp based on the input result of the light field determination model.

Wherein the method of determining the distance between the face of the target human body and the white light lamp of the smart cat eye may include:

the processor of the intelligent cat eye determines the distance between the face of the target human body and the white light lamp of the intelligent cat eye based on the position coordinates of the face of the target human body in the world coordinate system and the position coordinates of the white light lamp of the intelligent cat eye in the world coordinate system.

The input information of the light field determination model is a distance, specifically, in this embodiment, a distance between the face of the target human body and the white light of the smart cat eye; the output information of the light field determination model is a light field. The light field specifically refers to the intensity of light rays from any point in space to any direction.

In relation to the training of the light field determination model, a plurality of samples may be employed, each sample may include a light field of a white-light lamp that is optimal at a certain distance from the target volume; different samples in the plurality of samples may include different white light lamps, distances between the target bodies, and different light fields corresponding to the distances. In the process of training the light field determination model, a certain distance between the white light lamp and the target body can be used as input information to be input into the light field determination model in training, a result output by the light field determination model in training is obtained, the loss function of the time is calculated based on the result and the optimal light field of the white light lamp in the sample, and the light field determination model is updated based on reverse conduction of the loss function. When the iteration number of the light field determination model in the training reaches a preset threshold value, or an index (such as accuracy or recall ratio) in the iterative training of the light field determination model in the training does not change any more, it may be determined that the training is completed, and the light field determination model after the training is finally obtained is the light field determination model in the embodiment of the present application.

And the processor of the intelligent cat eye controls to turn on the white light lamp so that the white light lamp emits white light to the light emitting direction, and controls the main camera of the intelligent cat eye to adjust to the target focal length so as to shoot an image containing the face of the target human body in the target shooting direction.

It should be pointed out that, because the white light lamp is in with main camera the mounted position in the intelligence cat eye is probably different, consequently, the luminous direction of white light lamp with the current direction of shooing of main camera is probably also different, so the luminous direction of white light lamp and the direction of shooing of main camera are confirmed respectively to the scheme that this embodiment provided to make the more accurate face of shining the target human body of white light lamp, in order to play the warning effect to this target human body, and make the more accurate image of the face of shooting target human body of main camera, so that follow-up more accurate carry out processing such as analysis and warning.

Through adopting above-mentioned scheme, the intelligent cat eye just can have the target human body for the first time to detect in its detection range through infrared sensor, just control and open main camera, and confirm that the target human body is not the identity that allows to get into indoor such as under the condition of stranger through the image of gathering, detect the second distance between the face of target human body and the intelligent cat eye once more through laser radar, if this second distance is less than the second and predetermine the distance threshold value, then control the direction of adjustment white light lamp and main camera, make the face of white light lamp orientation target human body luminous and main camera shooting target human face. So, can avoid as long as infrared sensor detects someone and gets into its detection range and just open the extravagant problem of electric quantity that main camera brought, and, can also only be under the condition of the target human body that does not allow to get into indoor identity, the accurate position and the distance of the face of control redetection target human body, and the control is opened white light lamp and is shone to the face of this target human body, thereby make stranger appear in the time of outdoor night, can play the warning effect to this stranger through the white light lamp, indoor user's security has been promoted, the face of main camera and more accurate and clear shooting target human body under the cooperation of white light lamp is opened in the while control, so that when the follow-up looks for of relevant video, can be more clear accurate obtain the facial feature of target human body.

In the solution provided in this embodiment, the method may further include a process of predicting a movement trajectory of the target human body, and specifically, as shown in fig. 5, the process includes:

step 401: the processor of the smart cat eye determines historical movement information of the target human body based on N historical images containing the target human body; wherein N is an integer greater than or equal to 2;

here, the processing of step 401 may be processing started at any time after the target human body is determined not to be the identity permitted to enter the room in step 301, for example, after the target human body is determined not to be the identity permitted to enter the room in step 301, step 302 and step 401 may be triggered to be executed at the same time; alternatively, after determining that the target human body is not an identity that allows entry into a room in step 301, the execution of step 401 may be started at a point in time when N number of history images are currently stored.

N may be set according to practical situations, and may be, for example, 3, or may be 10, or more or less, and is not exhaustive here.

In addition, when the number of the historical images containing the target human body, which are acquired or stored by the main camera of the smart cat eye, is greater than N, N historical images can be selected from all the historical images containing the target human body for processing.

The processor of the smart cat eye determines historical movement information of the target human body based on N historical images including the target human body, and specifically may include:

the processor of the intelligent cat eye obtains N coordinates of the central point of the target human body in the N historical images containing the target human body in a camera coordinate system and time stamps corresponding to the N coordinates based on the N historical images containing the target human body and the time stamps corresponding to the N historical images;

converting the N coordinates of the central point of the target human body under a camera coordinate system into a world coordinate system to obtain N coordinates of the central point of the target human body under the world coordinate system;

and constructing historical movement information of the target human body based on the N coordinates of the central point of the target human body in the world coordinate system and the time stamps respectively corresponding to the N coordinates.

Step 402: determining a predicted movement track of the target human body after the current moment based on the historical movement information of the target human body;

the method specifically comprises the following steps: inputting the historical movement information into a track prediction model to obtain a predicted movement track of the target human body after the current moment, which is output by the track prediction model; at least one moment and a coordinate point of a target human body corresponding to the moment under a world coordinate system can be marked in the predicted movement track.

The trajectory prediction model may be a pre-trained model. The training sample of the model can be the moving tracks of multiple characters in multiple fields, and the coordinates of the multiple characters in multiple world coordinate systems are marked in the moving tracks.

When the trajectory prediction model is trained, the movement trajectory of the same character can be divided into two parts, for example, the movement trajectory has 10 minutes, and the movement trajectory in the first 5 minutes and the movement trajectory in the last 5 minutes can be divided into two parts; inputting the previous part of the moving track into a track prediction model in a training stage to obtain a prediction result output by the track prediction model in the training stage; and comparing the prediction result with the movement track of the next part to obtain a loss function of the training, and conducting and updating the track prediction model in the training stage reversely based on the loss function of the training. And carrying out iterative processing until the training is finished to obtain a trained track prediction model.

Step 403: and determining the predicted shooting directions respectively corresponding to the main camera at least one moment after the current moment and the predicted light emitting directions respectively corresponding to the white light lamp at least one moment within a preset time length after the current moment based on the predicted moving track of the target human body after the current moment.

The method specifically comprises the following steps: determining a predicted light emitting direction of a white light at the ith moment based on a coordinate point of the target human body under a world coordinate system at the ith moment in a predicted moving track of the target human body after the current moment and a coordinate position of the white light of the intelligent cat eye under the world coordinate system; and determining the predicted shooting direction of the main camera at the ith moment based on the coordinate point of the target human body in the world coordinate system corresponding to the ith moment in the predicted movement track of the target human body after the current moment and the coordinate position of the main camera of the intelligent cat eye in the world coordinate system.

After the processing, if the processor of the smart cat eye cannot determine the light emitting direction of the white light lamp and the current shooting direction of the main camera based on the position of the face of the target human body at any time after the current time, for example, the target human body is blocked, or the current main camera does not follow the movement of the target human body to cause that an image containing the target human body is not shot, the direction to which the white light lamp and the main camera are currently oriented can be controlled according to the predetermined predicted shooting direction and the predicted light emitting direction at the time, so that the shooting direction of the main camera and the direction of the white light illumination can accurately contain the target human body, especially the face containing the target human body.

It should be further noted that the foregoing processing in steps 401 to 403 may be performed in real time, that is, the processing in steps 401 to 403 may be performed once at each current time, and accordingly, the processor of the smart cat eye may delete the predicted shooting direction and the predicted light-emitting direction obtained at the historical time according to the actual situation, for example, the processor of the smart cat eye may only store the predicted shooting direction and the predicted light-emitting direction obtained within 10 seconds before the current time, and delete the predicted shooting direction and the predicted light-emitting direction obtained at other historical times; or, the processor of the smart cat eye may only store the predicted shooting direction and the predicted light emitting direction obtained within 3 seconds before the current time, and delete the predicted shooting direction and the predicted light emitting direction obtained at other historical times, which is not exhaustive here.

In addition, the scheme provided by this embodiment may further include: performing label setting and storage on the target human body in the image containing the target human body, and performing label setting and storage on other target bodies contained in the image containing the target human body; the other target bodies are other human bodies or other objects except the target human body, and the positions of the other target bodies and the target human body in the image are different.

The above-mentioned processing of carrying out label setting and carrying out label setting to other target bodies to the target human body can be to the image of the real-time collection of the main camera of intelligence cat eye, can be to the image of the real-time collection of the supplementary camera of intelligence cat eye again and go on. It should also be understood that the scheme provided by this embodiment is to perform label setting on all images in which a target human body appears and store the set labels and the corresponding images together.

Wherein the setting and storing the tag of the target human body in the image including the target human body may include: and setting and storing labels of the target human body in all the images containing the target human body. The set label can be determined according to the preset content of the user, for example, the user specifies in advance that the label is generated according to the appearance time and/or the appearance duration of a stranger, and then when the target human body appears at 1 point in the middle of the night, the label corresponding to the target human body is set to be 'XX day by 1 point in the early morning of the stranger'.

The other target bodies can determine whether to perform label setting according to the type of preset setting of the user, for example, the user presets to mark objects such as strange vehicles, bicycles and electric vehicles. The content of the tags for other objects may include: the type, number, appearance time, appearance duration, etc. of other objects. For example, once an unfamiliar vehicle appears in the image containing the target human body, the unfamiliar vehicle may be marked, and the label of the unfamiliar vehicle may be specifically "license plate number, appearance time of 1 point in the morning" or the like, which is not exhaustive here.

So, especially can carry out the setting of label when shooing stranger, stranger object appearing outdoors when the user has a rest night through above-mentioned processing to make the user take place to report on a case or provide under the condition of evidence, more quick convenient acquirees key material, and then guaranteed user's security.

Finally, it is also pointed out that the main camera of the smart cat eye and the auxiliary camera of the smart cat eye are both provided with transparent layers capable of generating a lotus leaf effect. The lotus leaf effect generally means that the surface of lotus leaves (or called lotus leaves) has the characteristics of hydrophobicity, self-cleaning and the like. The reason is that the surface of the lotus leaf is provided with a layer of hairy hairs and a plurality of tiny waxy particles, water cannot spread to other directions on the surface of the lotus leaf on the nanometer tiny particles, but forms a sphere, so that rolling water drops are formed, and the rolling water drops can take away dust on the surface of the lotus leaf, so that the surface of the lotus leaf is cleaned. The main camera of intelligence cat eye and the stratum lucidum that can produce the lotus leaf effect on the lens surface of the supplementary camera of intelligence cat eye is favorable to being in the main camera of intelligence cat eye and the supplementary camera surface of intelligence cat eye forms rolling water droplet in order to take away the dust on lens surface to can select the material that the transparency is high, it is right the main camera of intelligence cat eye and the luminousness influence of the supplementary camera of intelligence cat eye is less, and holistic shooting effect is good. In addition, the surface of the other part of the smart cat eye can also be provided with a material capable of generating a lotus leaf effect, and the material can be the same as or different from the material of the surfaces of the main camera of the smart cat eye and the auxiliary camera of the smart cat eye. Like this, follow the main camera of intelligence cat eye and the drop of water that the surface of the supplementary camera of intelligence cat eye rolled can be more fast roll and fall the main camera of intelligence cat eye and outside the supplementary camera of intelligence cat eye, be favorable to improving holistic cleanness and water-proof effects. Optionally, a material capable of generating a lotus effect may be formed on the surfaces of the main camera of the smart cat eye and the auxiliary camera of the smart cat eye by spraying, electroplating, dipping, or the like.

This disclosed embodiment is applied to intelligent cat eye, and this intelligent cat eye can include: the system comprises an infrared sensor, a laser radar, a main camera, a processor, a white light lamp, an auxiliary camera, an audio component and the like; the audio component may include a speaker, a microphone, and the like. In addition to the above components, the smart cat eye may further include: display, communication means, etc., which are not exhaustive here. In addition, the intelligent cat eye that this disclosed embodiment provided can set up the upper half at the house gate, can with the intelligent cat eye divides into indoor portion and outdoor portion. The indoor part can be a part of the intelligent cat eye facing the inside of the house, and the outdoor part can be a part of the intelligent cat eye facing the outside of the house. The indoor portion may include at least a display, a set of audio components (e.g., speaker, microphone, etc.); the outdoor portion of the smart cat eye may include at least: infrared sensor, laser radar, main camera, white light lamp etc. parts, of course, the outdoor part of intelligence cat eye can set up another group audio component (constitute by speaker and microphone) equally. It should be noted that the processor of the smart cat eye only needs to be disposed inside the smart cat eye, and here, whether the processor of the smart cat eye is located in the indoor portion or the outdoor portion of the smart cat eye is not limited.

According to the scheme provided by the embodiment, when the distance between the target human body and the intelligent cat eye is smaller than a first preset distance threshold value in the detection area of the infrared sensor on the intelligent cat eye, and the distance between the face of the target human body and the intelligent cat eye is smaller than a second preset distance threshold value through laser radar, whether the main camera is blocked or not can be analyzed through the current image collected by the main camera in real time, under the condition that the main camera is blocked, the target human body is warned through voice warning information, and the auxiliary camera is started to shoot the target human body; and under the condition that the main camera is not shielded, the white light lamp can be controlled to emit light towards the face of the target human body and the main camera is controlled to shoot the target human body. Therefore, the outdoor target human body can be timely and accurately identified and found by adopting the scheme, so that the warning and the deterrence are carried out under the condition that the distance between the target human body and the intelligent cat eye is too short, and the safety of the user in the room is ensured.

In a second aspect of the present disclosure, a control device for a smart cat eye is provided, as shown in fig. 6, the device includes:

the processor 61 is used for controlling the main camera to acquire images in real time under the condition that the infrared sensor detects that a first distance between a target human body and the smart cat eye is smaller than a first preset distance threshold value and the laser radar detects that a second distance between the face of the target human body and the smart cat eye is smaller than a second preset distance threshold value; judging whether the main camera is in a shielding state or not based on a current image acquired by the main camera in real time, if so, generating voice warning information, and sending the voice warning information through an audio component, wherein the voice warning information is used for reminding the target human body to remove a shielding object, starting an auxiliary camera and acquiring an image containing the target human body, which is obtained by the auxiliary camera through real-time shooting, and the auxiliary camera and the main camera are arranged at different positions; if the human body is not in the shielding state, based on the position of the face of the target human body, determining the light-emitting direction of a white light lamp, determining the target shooting direction and the target focal length of the main camera, controlling to turn on the white light lamp to enable the white light lamp to emit white light to the light-emitting direction, and controlling the main camera to be adjusted to the target shooting direction to shoot an image containing the face of the target human body at the target focal length;

an infrared sensor 62 for detecting a first distance between a target human body and the smart cat eye;

the laser radar 63 is used for detecting a second distance between the face of the target human body and the intelligent cat eye;

the main camera 64 is used for acquiring images in real time;

an auxiliary camera 65 for turning on and shooting an image including a target human body based on the control of the processor;

a white light lamp 66 for emitting white light to the light emitting direction based on the control of the processor;

and an audio component 67 for issuing voice warning information.

The infrared sensor 62 is used for detecting a human body in real time to obtain a current detection result;

the processor 61 is configured to determine whether a target human body exists in the detection range of the infrared sensor based on the current detection result, determine, if a target human body exists, a first distance between the target human body and the smart cat eye based on the current detection result, determine whether the first distance is smaller than a first preset distance threshold, if the first distance is smaller than the first preset distance threshold, acquire, in real time, an image including the target human body through the main camera, and otherwise, continue to determine, based on the current detection result, whether a target human body exists in the detection range of the infrared sensor; and if the target human body does not exist, continuously judging whether the target human body exists in the detection range of the infrared sensor or not based on the current detection result.

The device further comprises:

a communication section 68 for transmitting prompt information;

the processor 61 is configured to identify a face in the current image including the target human body acquired by the main camera to determine whether the target human body is an identity allowing entry into a room, and if so, control the communication component to send a prompt message to prompt a user to perform subsequent processing; if not, determining the current relative position of the face of the target human body based on the current image containing the target human body, and determining the target orientation of the laser radar based on the current relative position of the face of the target human body and the position of the laser radar; controlling the laser radar to perform distance acquisition under the orientation of the target so as to obtain a second distance between the face of the target human body and the intelligent cat eye; judging whether the second distance is smaller than a second preset distance threshold value or not, if not, returning to execute the process of determining the current relative position of the face of the target human body based on the current image containing the target human body, and determining the target orientation of the laser radar based on the current relative position of the face of the target human body and the position of the laser radar; and if the difference is smaller than the preset value, controlling the main camera to acquire images in real time.

The processor 61 is configured to input the current image including the target human body acquired by the main camera into a face detection model, and obtain position information of a face region including a face output by the face detection model; extracting a face image from a current image containing the target human body based on the position information of the face region; inputting the face image into a face recognition model to obtain the image similarity between the face image and a reference face image; the face image recognition model is a deep neural network model for face recognition, which is obtained by training a plurality of sample face images; the reference face image is a face image of a person allowed to enter a room and preset in the face image recognition module; judging whether the image similarity between the face image and the reference face image is greater than a preset similarity threshold value, and if so, determining that the target human body is an identity allowed to enter the room; otherwise, determining the target human body as an identity which is not allowed to enter the room.

The processor 61 is configured to input the current image including the target human body acquired by the main camera into a face detection model, so as to obtain an output result of the face detection model; judging whether the output result contains the position information of the face region of the face or not, and if so, obtaining the position information of the face region containing the face output by the face detection model; if not, determining the adjustment direction and the adjustment angle of the main camera based on the current image containing the target human body, adjusting the shooting angle of the main camera based on the adjustment direction and the adjustment angle, returning to execute the process of inputting the current image containing the target human body collected by the main camera into the face detection model to obtain the output result of the face detection model.

The processor 61 is configured to perform one of:

generating first prompt information containing the face image; controlling a communication component of the intelligent cat eye to send first prompt information to terminal equipment of a user so as to prompt the user whether to open a door;

determining the identity information of the target human body based on the face image, and generating second prompt information based on the identity information of the target human body; controlling the communication component to send second prompt information to the terminal equipment of the user so as to prompt the user whether to open the door;

determining the identity information of the target human body based on the face image, and generating third prompt information based on the identity information of the target human body; and controlling the audio component to convert the third prompt information into audio information, and playing the audio information to a user in a room to prompt the user whether to open the door.

The processor 61 is configured to input the distance between the face of the target human body and the white light lamp into a light field determination model, and determine the current light field of the white light lamp based on an input result of the light field determination model.

The processor 61 is configured to detect a current image acquired by the main camera; and if the current image does not contain the target human body, determining that the main camera is in a shielding state and storing the currently acquired image.

The device further comprises:

an electrostatic generating part 69 for generating an electrostatic pulse based on the control of the processor;

and the processor 61 is configured to control to turn on the electrostatic generating component to send an electrostatic pulse to an area where the main camera is located, under the condition that it is determined that the main camera is in a shielding state.

The processor 61 is configured to, after the audio component of the smart cat eye sends the target duration of the voice warning information, if it is determined that the main camera is continuously in a shielding state based on the image currently acquired by the main camera, obtain a first preset voice, and control the audio component to send the first preset voice;

The processor 61 is configured to determine historical movement information of the target human body based on N historical images including the target human body; wherein N is an integer greater than or equal to 2; determining a predicted movement track of the target human body after the current moment based on the historical movement information of the target human body; and determining the predicted shooting directions respectively corresponding to the main camera at least one moment after the current moment and the predicted light emitting directions respectively corresponding to the white light lamp at least one moment within a preset time length after the current moment based on the predicted moving track of the target human body after the current moment.

The processor 61 is configured to perform label setting and storage on the target human body in the image including the target human body, and perform label setting and storage on other target bodies included in the image including the target human body; the other target bodies are other human bodies or other objects except the target human body, and the positions of the other target bodies and the target human body in the image are different.

The surface of the main camera and the surface of the auxiliary camera are both provided with transparent layers capable of generating lotus leaf effect.

The control device that this embodiment provided can set up with in the intelligent cat eye. By adopting the scheme provided by the embodiment, the distance between the target human body and the intelligent cat eye in the detection area of the infrared sensor is smaller than a first preset distance threshold, under the condition that the distance between the face of the target human body and the intelligent cat eye is smaller than a second preset distance threshold, whether the main camera is blocked or not can be analyzed through the current image collected by the main camera in real time, under the condition that the main camera is blocked, the target human body is warned through voice warning information, and the auxiliary camera is started to shoot the target human body; and under the condition that the main camera is not shielded, the white light lamp can be controlled to emit light towards the face of the target human body and the main camera is controlled to shoot the target human body. Therefore, the outdoor target human body can be timely and accurately identified and found by adopting the scheme, so that the warning and the deterrence are carried out under the condition that the distance between the target human body and the intelligent cat eye is too short, and the safety of the user in the room is ensured.

It should be noted that, in the embodiment of the present disclosure, the division of each functional unit is schematic, and is only one logical functional division, and there may be another division manner in actual implementation. Each functional unit in the embodiments of the present disclosure may be integrated into one processing unit, each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method provided by the embodiments of the present disclosure. And the aforementioned storage medium includes: u disk, removable hard disk, read only memory, random access memory, magnetic or optical disk, etc. for storing program codes.

Fig. 7 is a block diagram of an electronic device according to an embodiment of the invention. As shown in fig. 7, the electronic apparatus includes: a memory 710 and a processor 720, the memory 710 having stored therein computer programs that are executable on the processor 720. The number of the memory 710 and the processor 720 may be one or more. The memory 710 may store one or more computer programs that, when executed by the electronic device, cause the electronic device to perform the methods provided by the above-described method embodiments.

The electronic device further includes:

and a communication interface 730, configured to communicate with an external device, and perform data interactive transmission.

If the memory 710, the processor 720 and the communication interface 730 are implemented independently, the memory 710, the processor 720 and the communication interface 730 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 7, but this is not intended to represent only one bus or type of bus.

Optionally, in an implementation, if the memory 710, the processor 720 and the communication interface 730 are integrated on a chip, the memory 710, the processor 720 and the communication interface 730 may complete communication with each other through an internal interface.

The embodiment of the present disclosure also provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions are run on a computer, the computer is caused to execute the method provided by the above method embodiment.

The embodiment of the present disclosure further provides a computer program product, where the computer program product is used to store a computer program, and when the computer program is executed by a computer, the computer may implement the method provided by the above method embodiment.

The embodiment of the disclosure also provides a chip, which is coupled with the memory, and is used for implementing the method provided by the embodiment of the method.

It should be understood that the processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or any conventional processor or the like. It is noted that the processor may be a processor supporting an Advanced reduced instruction set machine (ARM) architecture.

Further, optionally, the memory may include a read-only memory and a random access memory, and may further include a nonvolatile random access memory. The memory may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may include a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can include Random Access Memory (RAM), which acts as external cache Memory. By way of example, and not limitation, many forms of RAM are available. For example, Static Random Access Memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data rate Synchronous Dynamic Random Access Memory (DDR SDRAM), Enhanced SDRAM (ESDRAM), SLDRAM (SLDRAM), and Direct RAMBUS RAM (DR RAM).

In the above embodiments, the implementation may be wholly or partly realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the disclosure to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, bluetooth, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., Digital Versatile Disk (DVD)), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others. Notably, the computer-readable storage media referred to in this disclosure may be non-volatile storage media, in other words, non-transitory storage media.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

In the description of the embodiments of the present disclosure, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

In the description of the embodiments of the present disclosure, "/" indicates an OR meaning, for example, A/B may indicate A or B; "and/or" herein is merely an association describing an associated object, and means that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone.

In the description of the embodiments of the present disclosure, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of the present disclosure, "a plurality" means two or more unless otherwise specified.

The above description is only exemplary of the present disclosure and is not intended to limit the present disclosure, and any modification, equivalent replacement, or improvement made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.

Claims

1. A control method, characterized in that the method comprises:

2. The method of claim 1, further comprising:

step 202: the processor of the intelligent cat eye determines a first distance between the target human body and the intelligent cat eye based on the current detection result, judges whether the first distance is smaller than a first preset distance threshold value, and if the first distance is smaller than the first preset distance threshold value, acquires an image containing the target human body in real time through a main camera of the intelligent cat eye; otherwise, return to execute step 201.

3. The method of claim 2, further comprising:

step 301: the processor of the intelligent cat eye identifies the face in the current image which is acquired by the main camera of the intelligent cat eye and contains the target human body so as to judge whether the target human body is an identity allowing the target human body to enter the room, if not, the step 302 is executed; if so, controlling a communication component of the intelligent cat eye to send prompt information to prompt a user to execute subsequent processing;

4. The method of claim 3, wherein the identifying, by the processor of the smart cat eye, the face in the current image containing the target human body captured by the main camera of the smart cat eye to determine whether the target human body is an identity allowing the target human body to enter the room comprises:

5. The method according to claim 4, wherein the inputting, by the processor of the smart cat eye, the current image containing the target human body collected by the main camera of the smart cat eye into the face detection model to obtain the position information of the face region containing the face output by the face detection model, comprises:

6. The method of claim 4, wherein the controlling the communication component of the smart cat eye to send a prompt message to prompt the user to perform subsequent processing comprises one of:

the processor of the intelligent cat eye determines the identity information of the target human body based on the face image and generates second prompt information based on the identity information of the target human body; controlling a communication component of the intelligent cat eye to send second prompt information to the terminal equipment of the user so as to prompt the user whether to open the door;

7. The method of claim 1, further comprising:

and the processor of the intelligent cat eye inputs the distance between the face of the target human body and the white light lamp of the intelligent cat eye into a light field determination model, and determines the current light field of the white light lamp based on the input result of the light field determination model.

8. The method of claim 1, wherein the determining, by the processor of the smart cat eye, whether the primary camera is in an occluded state based on the current image captured by the primary camera in real time comprises:

a processor of the intelligent cat eye detects a current image acquired by the main camera; and if the processor of the intelligent cat eye determines that the current image does not contain the target human body, determining that a main camera of the intelligent cat eye is in a shielding state, and storing the current image.

9. The method of claim 8, further comprising:

and under the condition that the main camera of the intelligent cat eye is determined to be in a shielding state, the processor of the intelligent cat eye controls to start the static electricity generation component to send static electricity pulses to the area where the main camera is located.

10. The method of claim 1, further comprising:

11. The method according to any one of claims 1-10, further comprising:

step 402: the processor of the intelligent cat eye determines a predicted movement track of the target human body after the current moment based on the historical movement information of the target human body;

step 403: and the processor of the intelligent cat eye determines the predicted shooting directions respectively corresponding to the main camera at least one moment after the current moment and determines the predicted light emitting directions respectively corresponding to the white light at least one moment within a preset time length after the current moment based on the predicted moving track of the target human body after the current moment.

12. The method according to any one of claims 1-10, further comprising:

performing label setting and storage on the target human body in the image containing the target human body, and performing label setting and storage on other target bodies contained in the image containing the target human body; the other target bodies are other human bodies or other objects except the target human body, and the positions of the other target bodies and the target human body in the image are different.

13. The method of any of claims 1-10, wherein a surface of the primary camera of the smart cat eye and a surface of the secondary camera of the smart cat eye each have a transparent layer capable of creating a lotus effect.

14. A control device, characterized in that the device comprises:

the processor is used for controlling the main camera to acquire images in real time under the condition that the infrared sensor detects that a first distance between a target human body and the intelligent cat eye is smaller than a first preset distance threshold value and the laser radar detects that a second distance between the face of the target human body and the intelligent cat eye is smaller than a second preset distance threshold value; judging whether the main camera is in a shielding state or not based on a current image acquired by the main camera in real time, if so, generating voice warning information, and sending the voice warning information through an audio component, wherein the voice warning information is used for reminding the target human body to remove a shielding object, starting an auxiliary camera and acquiring an image containing the target human body, which is obtained by the auxiliary camera through real-time shooting, and the auxiliary camera and the main camera are arranged at different positions; if the human body is not in the shielding state, based on the position of the face of the target human body, determining the light-emitting direction of a white light lamp, determining the target shooting direction and the target focal length of the main camera, controlling to turn on the white light lamp to enable the white light lamp to emit white light to the light-emitting direction, and controlling the main camera to be adjusted to the target shooting direction to shoot an image containing the face of the target human body at the target focal length;

the main camera is used for acquiring images in real time;

and the audio component is used for giving out voice warning information.

15. The apparatus of claim 14,

the infrared sensor is used for detecting a human body in real time to obtain a current detection result;

the processor is used for judging whether a target human body exists in the detection range of the infrared sensor based on the current detection result, if so, determining a first distance between the target human body and the smart cat eye based on the current detection result, judging whether the first distance is smaller than a first preset distance threshold value, if so, acquiring an image containing the target human body in real time through the main camera, and otherwise, continuously judging whether the target human body exists in the detection range of the infrared sensor based on the current detection result; and if the target human body does not exist, continuously judging whether the target human body exists in the detection range of the infrared sensor or not based on the current detection result.

16. The apparatus of claim 15, further comprising:

a communication section for transmitting a prompt message;

the processor is used for identifying the face in the current image which is acquired by the main camera and contains the target human body so as to judge whether the target human body is an identity allowing the target human body to enter the room, and if so, the processor controls the communication part to send prompt information so as to prompt a user to execute subsequent processing; if not, determining the current relative position of the face of the target human body based on the current image containing the target human body, and determining the target orientation of the laser radar based on the current relative position of the face of the target human body and the position of the laser radar; controlling the laser radar to perform distance acquisition under the orientation of the target so as to obtain a second distance between the face of the target human body and the intelligent cat eye; judging whether the second distance is smaller than a second preset distance threshold value or not, if not, returning to execute the process of determining the current relative position of the face of the target human body based on the current image containing the target human body, and determining the target orientation of the laser radar based on the current relative position of the face of the target human body and the position of the laser radar; and if the difference is smaller than the preset value, controlling the main camera to acquire images in real time.

17. The apparatus of claim 16,

the processor is used for inputting the current image which is acquired by the main camera and contains the target human body into a face detection model to obtain the position information of a face area which is output by the face detection model and contains the face; extracting a face image from a current image containing the target human body based on the position information of the face region; inputting the face image into a face recognition model to obtain the image similarity between the face image and a reference face image; the face image recognition model is a deep neural network model for face recognition, which is obtained by training a plurality of sample face images; the reference face image is a face image of a person allowed to enter a room and preset in the face image recognition module; judging whether the image similarity between the face image and the reference face image is greater than a preset similarity threshold value, and if so, determining that the target human body is an identity allowed to enter the room; otherwise, determining the target human body as an identity which is not allowed to enter the room.

18. The apparatus of claim 17,

the processor is used for inputting the current image which is acquired by the main camera and contains the target human body into a face detection model to obtain an output result of the face detection model; judging whether the output result contains the position information of the face region of the face or not, and if so, obtaining the position information of the face region containing the face output by the face detection model; if not, determining the adjustment direction and the adjustment angle of the main camera based on the current image containing the target human body, adjusting the shooting angle of the main camera based on the adjustment direction and the adjustment angle, returning to execute the process of inputting the current image containing the target human body collected by the main camera into the face detection model to obtain the output result of the face detection model.

19. The apparatus of claim 17, wherein the processor is configured to perform one of:

generating first prompt information containing the face image; controlling the communication component to send first prompt information to terminal equipment of a user so as to prompt the user whether to open a door;

determining the identity information of the target human body based on the face image, and generating third prompt information based on the identity information of the target human body; and controlling the audio component to convert the third prompt message into audio information, and playing the audio information to the user in the room to prompt the user whether to open the door.

20. The apparatus of claim 14,

the processor is used for inputting the distance between the face of the target human body and the white light lamp into a light field determination model, and determining the current light field of the white light lamp based on the input result of the light field determination model.

21. The apparatus of claim 14, wherein the processor is configured to detect a current image captured by the main camera; and if the current image does not contain the target human body, determining that the main camera is in a shielding state and storing the current image.

22. The apparatus of claim 21, further comprising:

a static electricity generating part for generating a static electricity pulse based on control of the processor;

and the processor is used for controlling to start the static electricity generating component to send static electricity pulses to the area where the main camera is located under the condition that the main camera is determined to be in the shielding state.

23. The device according to claim 14, wherein the processor is configured to, after the audio component of the smart cat eye sends out the target duration of the voice warning information, if it is determined that the main camera is continuously in an occlusion state based on the image currently captured by the main camera, obtain a first preset voice, and control the audio component to send out the first preset voice;

24. The apparatus according to any of claims 14-23, wherein the processor is configured to determine historical movement information of the target human body based on N historical images containing the target human body; wherein N is an integer greater than or equal to 2; determining a predicted movement track of the target human body after the current moment based on the historical movement information of the target human body; and determining the predicted shooting directions respectively corresponding to the main camera at least one moment after the current moment and the predicted light emitting directions respectively corresponding to the white light lamp at least one moment within a preset time length after the current moment based on the predicted moving track of the target human body after the current moment.

25. The apparatus according to any one of claims 14-23, wherein the processor is configured to perform label setting and saving on the target human body in the image containing the target human body, and perform label setting and saving on other target bodies contained in the image containing the target human body; the other target bodies are other human bodies or other objects except the target human body, and the positions of the other target bodies and the target human body in the image are different.

26. The apparatus of any of claims 14-23, wherein a surface of the primary camera and a surface of the secondary camera each have a transparent layer capable of creating a lotus effect.

27. An electronic device, comprising:

one or more processors;

a memory communicatively coupled to the one or more processors;

one or more computer programs, wherein the one or more computer programs are stored in the memory, which when executed by the electronic device, cause the electronic device to perform the method of any of claims 1-13.

28. A computer-readable storage medium having stored thereon computer instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1 to 13.