WO2023056811A1

WO2023056811A1 - Distance detection method and apparatus, control method and apparatus, and storage medium and electronic device

Info

Publication number: WO2023056811A1
Application number: PCT/CN2022/117067
Authority: WO
Inventors: 邱榆清
Original assignee: Oppo广东移动通信有限公司
Priority date: 2021-10-08
Filing date: 2022-09-05
Publication date: 2023-04-13
Also published as: CN113920195A

Abstract

A distance detection method, a control method, a distance detection apparatus, a control apparatus, a computer-readable storage medium and an electronic device. The distance detection method comprises: acquiring a facial image of a target user that is collected by an image collection device; determining, from the facial image, imaging sizes of at least two preset facial parts; and determining the distance between the target user and the image collection device according to the imaging sizes of the at least two preset facial parts. The accuracy of distance detection is improved, and the hardware cost is relatively low.

Description

Distance detection method, control method, device, storage medium and electronic equipment

This application claims the priority of the Chinese patent application with the application date of October 8, 2021, the application number 202111172688.8, and the name "distance detection method, control method, device, storage medium and electronic equipment". The contents are incorporated herein by reference.

technical field

The present disclosure relates to the technical field of computer vision, and in particular to a distance detection method, a control method, a distance detection device, a control device, a computer-readable storage medium and electronic equipment.

Background technique

As people's demand for intelligent electronic equipment is getting higher and higher, some intelligent functions need to be realized by detecting the distance between people and equipment. For example, when the mobile phone detects that the user is close to the mobile phone in the off-screen state, it will automatically wake up the screen; when the access control system detects that someone is approaching, it will automatically trigger the process of performing identity verification or opening the door, and so on.

However, related technologies have limited accuracy when detecting the distance between a person and a device, thereby limiting the application of the above functions.

Contents of the invention

The disclosure provides a distance detection method, a control method, a distance detection device, a control device, a computer-readable storage medium and electronic equipment.

According to the first aspect of the present disclosure, there is provided a distance detection method, comprising: acquiring a face image of a target user collected by an image acquisition device; determining at least two images of preset parts of the face in the face image Size: determining the distance between the target user and the image acquisition device according to the imaging sizes of the at least two preset parts of the face.

According to a second aspect of the present disclosure, a distance detection method is provided, including: acquiring a face image of a target user captured by an image acquisition device; determining at least one of The first preset part of the face; according to the imaging size of the first preset part of the face in the face image, at least one second face is determined in the preset part of the face in the face image Preset part: determining the distance between the target user and the image acquisition device according to the imaging size of the second preset part of the face in the face image.

According to the third aspect of the present disclosure, there is provided a control method, including: obtaining the distance between the target user and the image acquisition device, the distance is detected according to the distance detection method of the first or second aspect above; according to The distance generates a corresponding control command.

According to a fourth aspect of the present disclosure, there is provided a distance detection device, including: an image acquisition module configured to acquire a face image of a target user captured by an image acquisition device; an imaging size determination module configured to Determine the imaging sizes of at least two preset parts of the face in the face image; the distance determination module is configured to determine the distance between the target user and the image acquisition device according to the imaging sizes of the at least two preset parts of the face the distance between.

According to a fifth aspect of the present disclosure, a distance detection device is provided, including: an image acquisition module configured to acquire a face image of a target user captured by an image acquisition device; a first preset face part determination module configured to It is configured to determine at least one first preset human face part in the preset human face parts in the human face image; the second preset human face part determination module is configured to The imaging size of the first preset part of the face, at least one second preset part of the face is determined in the preset parts of the face in the face image; the distance determination module is configured to be based on the face image The imaging size of the preset part of the second human face is used to determine the distance between the target user and the image acquisition device.

According to a sixth aspect of the present disclosure, there is provided a control device, including: a distance acquisition module configured to acquire the distance between the target user and the image acquisition device, the distance is detected according to the distance of the first or second aspect above The method is detected; the control command generation module is configured to generate a corresponding control command according to the distance.

According to a seventh aspect of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the distance detection method of the above-mentioned first or second aspect and its possible implementations are implemented way, or realize the control method of the above third aspect and its possible realization ways.

According to an eighth aspect of the present disclosure, there is provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the executable instructions to Executing the distance detection method in the first or second aspect and possible implementations thereof, or executing the control method in the third aspect and possible implementations thereof.

Description of drawings

FIG. 1 shows a schematic diagram of a system architecture in this exemplary embodiment;

FIG. 2 shows a schematic structural diagram of an electronic device in this exemplary embodiment;

Fig. 3 shows a flow chart of a distance detection method in this exemplary embodiment;

Fig. 4 shows a schematic diagram of the imaging size of the face image and the preset parts of the face in this exemplary embodiment;

FIG. 5 shows a flow chart of determining the imaging size of a preset part of a face in this exemplary embodiment;

Fig. 6 shows the schematic diagram that detects iris by iris detection model in this exemplary embodiment;

FIG. 7 shows a schematic diagram of determining candidate distances through the imaging width of a face in this exemplary embodiment;

FIG. 8 shows a flowchart of another distance detection method in this exemplary embodiment;

FIG. 9 shows a flowchart of another distance detection method in this exemplary embodiment;

FIG. 10 shows a flowchart of a control method in this exemplary embodiment;

Fig. 11 shows a schematic structural diagram of a distance detection device in this exemplary embodiment;

Fig. 12 shows a schematic structural diagram of another distance detection device in this exemplary embodiment;

Fig. 13 shows a schematic structural diagram of another distance detection device in this exemplary embodiment;

Fig. 14 shows a schematic structural diagram of another distance detection device in this exemplary embodiment;

Fig. 15 shows a schematic structural diagram of a control device in this exemplary embodiment;

Fig. 16 shows a schematic structural diagram of another control device in this exemplary embodiment.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details being omitted, or other methods, components, devices, steps, etc. may be adopted. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and/or processor means and/or microcontroller means.

In related technologies, electronic devices are equipped with distance sensors, which implement distance sensing by emitting infrared signals, but this increases hardware costs, and the distance sensors are easily affected by the environment, resulting in reduced accuracy.

In view of the above problems, exemplary embodiments of the present disclosure firstly provide a distance detection method. The system architecture and application scenarios of the operating environment in this exemplary embodiment will be exemplarily described below in conjunction with FIG. 1 .

FIG. 1 shows a schematic diagram of a system architecture, and the system architecture 100 may include an image acquisition device 110 and a processing device 120 . Wherein, the image acquisition device 110 may be a camera, which is used to collect the face image of the target user; the processing device 120 may be a mobile phone, a tablet computer, a desktop computer, a notebook computer, etc., and is used to perform the distance detection method in this exemplary embodiment , by processing the face image to determine the distance between the target user and the image acquisition device 110 .

FIG. 1 shows that the image acquisition device 110 and the processing device 120 are two independent devices, which can be connected through a wired or wireless communication link for data interaction.

In an implementation manner, the image acquisition device 110 and the processing device 120 may also be integrated into one device. Exemplarily, the mobile phone has a built-in camera module, such as the camera module can include a front camera, which is equivalent to the image acquisition device 110; the mobile phone can collect the face image of the target user and perform a distance detection method to determine the distance between the target user and the mobile phone Furthermore, when the distance is relatively short, the mobile phone can send relevant information reminding the user to pay attention to the distance of the mobile phone and protect the eyes. Alternatively, the access control system includes a monitoring camera and a micro-control unit, the monitoring camera is equivalent to the image acquisition device 110, and the micro-control unit is equivalent to the processing device 120; the access control system collects the face image of the target user through the monitoring camera, and executes A distance detection method to determine the distance between the target user and the access control system; furthermore, when the distance is relatively short, the access control system can trigger the process of performing identity verification or opening the door.

Exemplary embodiments of the present disclosure also provide an electronic device for performing the above-mentioned distance detection method, and the electronic device may be the above-mentioned processing device 120 . Generally, the electronic device may include a processor and a memory, the memory is used to store executable instructions of the processor, and the processor is configured to execute the above-mentioned distance detection method by executing the executable instructions.

The structure of the electronic device will be described below by taking the mobile terminal 200 in FIG. 2 as an example. Those skilled in the art will appreciate that, in addition to components specifically intended for mobile purposes, the configuration in Fig. 2 can also be applied to equipment of a stationary type.

As shown in Figure 2, the mobile terminal 200 may specifically include: a processor 201, a memory 202, a bus 203, a mobile communication module 204, an antenna 1, a wireless communication module 205, an antenna 2, a display screen 206, a sensor module 207, and an audio module 208 , a power supply module 209 and a camera module 210 .

Processor 201 may include one or more processing units, for example: processor 210 may include AP (Application Processor, application processor), modem processor, GPU (Graphics Processing Unit, graphics processing unit), ISP (Image Signal Processor, image signal processor), controller, encoder, decoder, DSP (Digital Signal Processor, digital signal processor), baseband processor and/or NPU (Neural-Network Processing Unit, neural network processor), etc. In this exemplary embodiment, the distance detection method can be performed by an AP, GPU or DSP, etc. When the method involves neural network-related processing, it can be performed by an NPU. For example, the NPU can load neural network parameters and perform neural network related processing. algorithmic instructions.

An encoder encodes (i.e. compresses) an image or video to reduce the data size for storage or transmission. The decoder can decode (ie decompress) the coded data of the image or video to restore the image or video data. The mobile terminal 200 may support one or more encoders and decoders. In this way, the mobile terminal 200 can process images or videos in multiple encoding formats, such as: JPEG (Joint Photographic Experts Group, Joint Photographic Experts Group), PNG (Portable Network Graphics, portable network graphics), BMP (Bitmap, bitmap), etc. Image format, MPEG (Moving Picture Experts Group, moving picture expert group) 1, MPEG2, H.263, H.264, HEVC (High Efficiency Video Coding, high-efficiency video coding) and other video formats.

The processor 201 can form a connection with the memory 202 or other components through the bus 203 .

Memory 202 may be used to store computer-executable program code, which includes instructions. The processor 201 executes various functional applications and data processing of the mobile terminal 200 by executing instructions stored in the memory 202 . The memory 202 can also store application data, such as storing images, videos and other files.

The communication function of the mobile terminal 200 can be realized by the mobile communication module 204, the antenna 1, the wireless communication module 205, the antenna 2, the modem processor and the baseband processor. Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. The mobile communication module 204 can provide 2G, 3G, 4G, 5G and other mobile communication solutions applied on the mobile terminal 200 . The wireless communication module 205 can provide wireless communication solutions such as wireless local area network, bluetooth, and near field communication applied on the mobile terminal 200 .

The display screen 206 is used to implement a display function, such as displaying a user interface, images, videos, and the like. The sensor module 207 is used to implement various sensing and detection functions, such as a pressure sensor, a gyroscope sensor, etc., to realize the detection of touch pressure and device pose. The audio module 208 is used to implement audio functions, such as playing audio, collecting voice, and so on. The power module 209 is used to implement power management functions, such as charging the battery, supplying power to the device, and monitoring the state of the battery.

The camera module 210 may include a lens 2101 , an image sensor 2102 , an optical anti-shake system 2103 and other components. The lens 2101 is used for imaging and adjusting the optical path; the image sensor 2102 is used for collecting optical signals and converting them into digital signals, which can be further transmitted to the ISP for processing; the optical anti-shake system 2103 is used for stabilizing the lens 2101 to prevent imaging shake, Improve image quality. The camera module 210 can be used to capture the face image of the target user.

The distance detection method of this exemplary embodiment will be described below in conjunction with FIG. 3. FIG. 3 shows an exemplary flow of the distance detection method, which may include:

Step S310, acquiring the face image of the target user collected by the image acquisition device;

Step S320, determining the imaging sizes of at least two preset parts of the face in the face image;

Step S330: Determine the distance between the target user and the image acquisition device according to the imaging sizes of the at least two preset parts of the face.

Based on the above method, on the one hand, the distance between the target user and the image acquisition device is determined by combining the imaging sizes of at least two preset parts of the face in the face image, which can reduce the instability caused by the imaging instability of a single preset part of the face. In addition, the face image is less affected by environmental conditions such as illumination, which is conducive to improving the accuracy of distance detection. On the other hand, this solution can be realized based on image acquisition devices such as cameras, without special configuration of distance sensors, and has low hardware cost, which is especially suitable for deployment in mobile scenarios such as mobile phones.

Each step in Fig. 3 is described in detail below.

Referring to FIG. 3 , in step S310 , the face image of the target user collected by the image collection device is acquired.

The target user may be a user located in front of the lens of the image capture device. For example, the image collection device may be a front camera of a mobile phone. When a user picks up the mobile phone or is using the mobile phone, the front camera collects the face image of the user, and the user is the target user.

In some specific scenarios, functions related to distance detection need to be implemented by the user facing the device. For example, the above functions of automatically waking up the screen of the mobile phone, prompting the user to pay attention to the distance of the mobile phone, and triggering identity verification of the access control system all need to be executed when the user faces the device. Based on this, the face image of the target user collected by the image acquisition device may be a frontal face image. If the image acquisition device collects a non-frontal face image of a certain user, the user may not need the above-mentioned relevant functions, that is, no Detect the distance between the user and the device. For example, if the mobile phone captures a user's overlooking face image, the user may not be using the mobile phone, and the access control system captures a user's profile image, and the user may be a passerby passing in front of the access control system. Therefore, there is no need to process such face images. In one embodiment, the human face image acquired in step S310 is a frontal human face image, and if the image acquisition device acquires a non-frontal human face image, no subsequent processing is performed on the non-frontal human face image. The present disclosure does not limit the specific manner of detecting whether the face image is a frontal face image. Exemplarily, the eye sight direction in the face image can be detected, if the eye sight direction is looking straight ahead (that is, looking at the image acquisition device), then it is judged that the face image is a frontal face image; The key points of the face, and then judge whether the key points of the face on the left and the key points of the face on the right are symmetrically distributed, and if they are symmetrically distributed or approximately symmetrically distributed, then it is judged that the face image is a frontal face image.

In an implementation manner, preprocessing may be performed on the face image. For example, the face image includes image content other than the face. If a part of the body of the target user is captured, only the image of the face part can be retained by cropping; in order to facilitate subsequent processing, the face image can be converted into a unified Size, such as 480*480, or numerical normalization of face images, etc.

Continuing to refer to FIG. 3 , in step S320 , the imaging sizes of at least two preset parts of the face are determined in the face image.

The preset face part refers to a part whose size is relatively fixed and does not vary significantly from person to person. In other words, the size difference of the preset face parts of different people is generally small. In this exemplary embodiment, the preset parts of the human face include but are not limited to: face, iris, pupil and so on. Among them, the size of the face includes the width of the face and the height of the face, and the width of the face varies from person to person to a lesser degree; The iris is approximated as a circle, and the diameter of the circle is the iris diameter. The iris diameter of an adult is usually about 11.8mm, and the deviation is very small; the pupil size generally refers to the interpupillary distance (that is, the distance between the left and right pupils, also known as the pupil Interpupillary distance), the interpupillary distance of adults is usually 58~61mm, and the degree of interpupillary distance varies from person to person.

The size mentioned above is the actual size, and the size of the preset part of the face in the face image is the imaging size. Due to the perspective relationship, the closer the distance between the target user and the image acquisition device, the larger the imaging size of the preset part of the face, and the farther the distance between the target user and the image acquisition device, the larger the imaging size of the preset part of the face. Small. Therefore, the distance between the target user and the image acquisition device can be determined according to the imaging size of the preset part of the face.

Referring to FIG. 4 , in the face image, the imaging sizes of three preset parts of the face can be determined, which are the imaging width d _face of the face, the imaging diameter d _iris of the iris, and the imaging distance d _pupil of the pupils. The imaging size can be the pixel size of the preset part of the face in the face image, or the projection size of the preset part of the face on the image plane of the face image. The dimension of the pixel size and the projection size are different. The meaning expressed is the same.

In one embodiment, referring to FIG. 5 , determining the imaging sizes of at least two preset parts of the face in the face image may include the following steps S510 and S520:

Step S510, by detecting the key points of the face in the face image, to determine the preset part of the face in the face image;

Step S520: Determine the imaging size of the preset part of the face according to the pixels covered by the preset part of the face in the face image.

Wherein, the key points of the human face may be key points of preset parts of the human face, for example, may include key points of facial outline, key points of iris, key points of pupils, and the like.

In one embodiment, a model (such as a neural network) for detecting the key points of the human face may be pre-trained, a human face image is input into the model, and the key points of the human face are output through the model.

General face key point detection models or algorithms may not be able to detect iris key points and pupil key points. A certain input size makes the image lose detail information to a certain extent, making it difficult to detect such small parts as iris and pupil. In one embodiment, the above-mentioned detection of key points of the face in the face image to determine the preset position of the face in the face image may include the following steps:

Detect face key points in the face image, the face key points include facial contour key points and eye key points;

Determine the face in the face image according to the key points of the face contour;

The eye image is intercepted from the human face image based on the eye key point, and the iris key point and/or pupil key point are detected in the eye image to determine the iris and/or pupil in the human face image.

Exemplarily, the face contour key points and eye key points in the face image can be detected by a general face key point detection model. Exemplarily, the face image can be converted to a size of 320*320, input Face key point detection model, which outputs information of 49 face key points, from which the key points of the face contour and the key points of the eyes are determined. Determine the face in the face image according to the key points of the face contour, for example, the position information of the face can be output. The position of the eye area in the face image is determined according to the key points of the eye, and then the eye image is cut out from the face image. It should be understood that the eye image may be cut from the original high-resolution face image so that the eye image also has a high resolution; or in the case of a low-resolution eye image, it may be up-sampled. Furthermore, the iris key points and/or pupil key points in the eye image can be detected by the iris or pupil detection model, so as to obtain the required information of the preset parts of the face.

According to the key points of the human face, the preset position of the human face in the face image can be determined, for example, the outer boundary of the preset part of the human face can be determined according to the key points of the human face, and the outer boundary can be used to characterize the position of the preset position of the human face, or according to The outer boundary extracts the mask (mask) of the preset part of the face, which can also represent the position of the preset part of the face.

Fig. 6 shows that the image of the eye area is input into the iris detection model, which is a pre-trained image segmentation network and can output iris information, which is the mask of the iris area.

According to the pixel points covered by the preset part of the face in the face image, the size of the preset part of the face can be expressed in pixels to obtain the pixel size of the preset part of the face, or convert the pixel size to the projection size , the two sizes are the imaging sizes of the preset parts of the face, and the disclosure does not limit which one is used specifically.

The calculation method of the imaging size of each preset part of the face will be exemplified below.

In one embodiment, when the preset part of the face includes a face, determining the imaging size of the preset part of the face according to the pixels covered by the preset part of the face in the face image may include the following steps :

In the pixel points covered by the face in the face image, the minimum coordinate value and the maximum coordinate value along the direction of the preset coordinate axis are obtained, and the imaging width of the face is determined according to the minimum coordinate value and the maximum coordinate value.

Wherein, the preset coordinate axis direction is the width direction of the face, which is generally the horizontal direction in the face image (related to the direction of the face image itself, which is not limited in this disclosure), that is, the x-axis direction. Obtain the minimum x-coordinate value and maximum x-coordinate value of the face pixels, and subtract them to obtain the imaging width of the face.

In one embodiment, the facial symmetry axis can be determined according to the pixels covered by the face in the face image; for example, the normal line can be generated at the pixel points of the facial contour to detect the pixel points of the face Whether to be symmetric about this normal, if so, this normal is the axis of symmetry of the face. Then, the vertical direction of the facial symmetry axis is used as the preset coordinate axis direction, and the minimum coordinate value and the maximum coordinate value are determined in the face pixel points, and the subtraction of the two is the imaging width of the face.

In one embodiment, when the preset part of the face includes the iris, determining the imaging size of the preset part of the face according to the pixels covered by the preset part of the face in the face image may include the following steps:

Determine the imaging area of the iris according to the number of pixels contained in the iris in the face image;

The imaging diameter of the iris is determined according to the imaging area of the iris.

Referring to the above-mentioned figure 6, the number of pixels contained in the iris in the face image can be counted according to the mask of the iris area, and the number of pixels is the imaging area Siris of the _iris , and then the iris is calculated by the following formula (1): The imaging diameter d _iris :

The imaging diameter d _iris is also equivalent to twice the average value of the major and minor axes of the ellipse of the iris.

In one embodiment, when the preset part of the face includes the pupil, determining the imaging size of the preset part of the face according to the pixels covered by the preset part of the face in the face image may include the following steps:

The center point of the left pupil and the center point of the right pupil are determined respectively according to the pixel points covered by the left pupil and the right pupil in the face image. Specifically, the median value of the abscissa and ordinate can be found in the pixels of the left pupil (the median can also be replaced by the average value), and the point where the median of the abscissa and ordinate is located is the center of the left pupil point. In the same way, the center point of the right pupil can be obtained.

Determine the distance between the center point of the left pupil and the center point of the right pupil, that is, the imaging distance of the pupils.

In one embodiment, the above-mentioned determination of the imaging sizes of at least two preset parts of the face in the face image may include the following steps:

Input the face image into the pre-trained face size detection model to output the imaging width of the face in the face image;

Input the face image and the imaging width of the face into the pre-trained iris size detection model or pupil size detection model to output the imaging diameter of the iris or the imaging distance of the pupils in the face image.

Generally, since the face occupies a large area in the face image, it is less affected by the low resolution of the image, and it is easy to achieve more accurate size detection. In contrast, the iris or pupil itself is small in size, occupies a small area in the face image, is less affected by the low resolution of the image, and is not easy to achieve accurate size detection. Therefore, when detecting iris size or pupil size, the imaging width of the face can be used as one-dimensional information, which can be input into the iris size detection model or pupil size detection model together with the face image to provide a reference, which is beneficial to improve the iris size or pupil size. Accuracy of pupil size.

Determining the imaging width of the face in the face image;

determining a first size range for the iris according to the imaging width of the face and the first scale range;

The imaging diameter of the iris is determined in the face image, and if the imaging diameter is within the first size range, it is determined that the imaging diameter is valid.

Wherein, the first ratio range is a ratio range of the face width to the iris diameter. Since the size of the face width and the iris diameter are relatively fixed, and the ratio of the two is also relatively fixed, the first ratio range is a range determined based on experience, and the ratio of the face width to the iris diameter is usually within this range. Therefore, first determine the imaging width of the face, and then calculate the first size range of the corresponding iris through the first ratio range, that is, assuming that the ratio of the face width to the iris diameter is in the first ratio range, the iris diameter should be in the within the first dimension. Furthermore, after determining the imaging diameter of the iris, judge whether the imaging diameter is accurate through the first size range, if the imaging diameter is within the first size range, then the result of determining the imaging diameter is accurate and effective; otherwise, if the imaging diameter If it is not within the first size range, the result of determining the imaging diameter is inaccurate and may not be retained.

Determining the imaging width of the face in the face image;

determining a second size range for the pupil according to the imaging width of the face and the second scale range;

The imaging distance of the pupils is determined in the face image, and if the imaging distance is within the second size range, it is determined that the imaging distance is valid.

Wherein, the second ratio range is a ratio range between the face width and the interpupillary distance. Since the size of the face width and the interpupillary distance are relatively fixed, the ratio of the two is also relatively fixed. The second ratio range is a range determined based on experience, and the ratio of the face width to the interpupillary distance is usually within this range. Therefore, first determine the imaging width of the face, and then calculate the corresponding second size range of pupils through the second ratio range, that is, assuming that the ratio of the face width to the interpupillary distance is in the second ratio range, the interpupillary distance should be in the within the second size range. Furthermore, after determining the imaging distance of the pupils, judge whether the imaging distance is accurate through the second size range, if the imaging distance is within the second size range, it is determined to be accurate and effective, otherwise it may not be retained.

Continuing to refer to FIG. 3 , in step S330 , the distance between the target user and the image acquisition device is determined according to the imaging sizes of the above-mentioned at least two preset parts of the face.

Wherein, the imaging size of each preset part of the face can be used independently to determine the distance between the target user and the image acquisition device. However, the imaging of a preset part of a single face may be unstable, resulting in an inability to accurately obtain its imaging size. For example, the face image may have closed eyes, occlusion, dark environment, etc., resulting in the inability to determine one or more preset parts of the face (such as the pupil and iris cannot be determined when the eyes are closed, and the face cannot be determined when the face is occluded). In the dark environment, the recognition of the preset parts of the face is affected), and its imaging size cannot be obtained; there is a relative angle between the face of the target user and the lens of the image acquisition device, so that the collected face image is not a completely frontal face image , leading to the error of the imaging size of the preset part of the face; when the resolution of the face image is low or the part is not clear, there will be errors in the detection of the key points of the face and the determination of the preset part of the face, which will lead to human The error of the imaging size of the preset part of the face, especially when the imaging size is represented by the pixel size, the area occupied by the preset part of the face with a smaller size such as the iris is often less than 20 pixels, such an error of one pixel will cause such a person Large errors in the imaging size of the preset parts of the face; errors in the imaging size of the preset parts of the face caused by defects such as distortion, noise, and distortion in the imaging process, and so on. In this exemplary embodiment, the distance between the target user and the image acquisition device is determined by the imaging size of various preset parts of the face, which can reduce the impact of the error of the imaging size of a single preset part of the face, and has It is beneficial to improve the accuracy of distance detection.

In one embodiment, the determination of the distance between the target user and the image acquisition device according to the imaging sizes of the at least two preset parts of the face may include the following steps:

The candidate distance between the target user and the image acquisition device is determined according to the ratio of the actual size of each preset part of the face to the imaging size and the imaging parameters of the image acquisition device.

Based on the candidate distance corresponding to the imaging size of each preset part of the face, the distance between the target user and the image acquisition device is determined.

As shown in FIG. 7, taking the face as an example, D _face represents the actual width of the face, d _face represents the imaging width of the face, and Z _face represents the distance between the target user and the image acquisition device. Determined by the imaging width, it is called the candidate distance corresponding to the imaging width of the face; z represents the imaging parameter of the image acquisition device. When d _face is the projection size, the imaging parameter is related to the focal length and field angle of the image acquisition device , when d _face is the pixel size, the imaging parameter is related to the focal length of the image acquisition device, the angle of view, the resolution of the face image, and the size of the image sensor. According to the relationship of similar triangles, there is the following formula (2):

Accordingly, the candidate distance Z _face corresponding to the imaging width of the face can be calculated. Similarly, the candidate distance Z _iris corresponding to the imaging diameter of the iris and the candidate distance Z _pupil corresponding to the imaging distance of the pupils can be obtained.

Furthermore, by combining the above two or more candidate distances, the distance between the target user and the image acquisition device can be determined as a result of the distance detection. For example, an average or weighted average may be calculated for multiple candidate distances to obtain the final distance.

In one embodiment, determining the distance between the target user and the image acquisition device based on the candidate distance corresponding to the imaging size of each preset part of the face may include the following steps:

Determine the weight of each preset face part according to the imaging size of at least one preset face part or at least one candidate distance;

Based on the weight of each preset part of the face, the candidate distance corresponding to the imaging size of each preset part of the face is weighted to obtain the distance between the target user and the image acquisition device.

Generally, the larger the actual size of the preset part of the face, the smaller the error of the imaging size of the preset part of the face in the low-resolution face image, and the actual size of the preset part of the face varies from person to person The higher the degree is, the more unstable the actual size of the preset part of the face is. For example, according to the actual size, there is face width > interpupillary distance > iris diameter. When the resolution of the face image is low, the errors of the imaging sizes of the three preset parts of the face increase in turn, from the low-resolution In terms of factors, you can set decreasing weights for the face, pupil, and iris; however, according to the degree of instability of the actual size, there is face width > interpupillary distance > iris diameter, that is, the three preset parts of the face The error of the actual size decreases successively. From the perspective of factors that are unstable in the actual size, increasing weights can be set for the face, pupil, and iris. Therefore, the weight of each preset part of the face can be determined by balancing these two factors. For example, if any preset part of the face is selected, the larger the imaging size or the smaller the candidate distance corresponding to the imaging size, It shows that the closer the distance between the target user and the image acquisition device, the clearer the pupil or iris information can be easily obtained in the face image at this time, that is, the influence of the low resolution factor is less, so the pupil or iris can be set higher On the contrary, the smaller the imaging size of the above-mentioned preset parts of the face or the larger the candidate distance corresponding to the imaging size, the farther the distance between the target user and the image acquisition device is. Clearer pupil or iris information is obtained, that is, the influence of low-resolution factors is greater, so a higher weight can be set for the face.

Exemplarily, when the two preset parts of the face and the iris are selected for distance detection, the weight of each preset part of the face can be determined by the following formula (3):

Among them, _wiris represents the weight of the iris, and w _face represents the weight of the face; e1 is a linear coefficient, which can be an empirical value. Furthermore, the distance Z between the target user and the image acquisition device can be determined by the following formula (4):

Z＝w _iris Z _iris +w _face Z _face (4)

When selecting the face, pupil and iris three preset parts of the face for distance detection, the weight of each preset part of the face can be determined by the following formula (5):

Among them, w _pupil represents the weight of the pupil; both e2 and e3 are linear coefficients, which can be empirical values. Furthermore, the distance Z between the target user and the image acquisition device can be determined by the following formula (6):

Z＝w _iris Z _iris +w _pupil Z _pupil +w _face Z _face (6)

Therefore, weighting the candidate distances corresponding to the imaging sizes of more than two preset parts of the face according to actual factors, and combining the information of different preset parts of the face is beneficial to output accurate distance detection results.

Exemplary embodiments of the present disclosure also provide another distance detection method. FIG. 8 shows an exemplary flow of the distance detection method, which may include the following steps S810 to S840:

Step S810, acquiring the face image of the target user collected by the image collection device.

For the specific implementation manner of this step, please refer to the relevant content of step S310.

Step S820, determining at least one first predetermined face part in the face preset part in the face image.

Wherein, the preset parts of the face include but not limited to: face, pupil, iris, and so on. The first preset part of the human face is used for preliminary estimation of the distance between the target user and the image acquisition device. Any one of the preset parts of the face can be selected as the first preset part of the face.

In one embodiment, the preset part of the face with the largest imaging size in the face image can be determined as the first preset part of the face. For example, the size of the face is generally larger than the pupil and iris, and the face can be determined as the first preset part. A preset part of a face.

In one embodiment, the preset face part whose imaging size is greater than a predetermined size threshold in the face image can be determined as the first preset part of the face, so as to ensure that the imaging size of the first preset part of the face will not be too large. Small, reduce the error.

It should be noted that the present disclosure does not limit the number of preset parts of the first human face.

Step S830, according to the imaging size of the first predetermined face part in the face image, determine at least one second preset part of the face in the preset parts of the face in the face image.

The second preset part of the face is used to accurately calculate the distance between the target user and the image acquisition device, and may be determined after considering two aspects of the low resolution factor and the unstable factor of the actual size. Generally, in the case where the influence of the low-resolution factor is small, the preset face part with a smaller actual size and more stable tends to be used as the second preset part of the face. In this exemplary embodiment, according to the imaging size of the first preset part of the face in the face image, the distance between the target user and the image acquisition device can be preliminarily estimated, and then the influence of the low-resolution factor can be determined.

In one embodiment, the first threshold may be preset for the imaging width of the face, and step S830 may include:

When the imaging width of the face in the face image is greater than the first threshold, the iris in the face image is determined as the second preset part of the face;

When the imaging width of the face in the face image is smaller than the first threshold, the face is determined as the second preset part of the face.

Wherein, the first threshold may be determined according to experience and parameters of the image acquisition device, for example, for a certain type of mobile phone, the first threshold may be 110 pixels. When the imaging width of the face in the face image is greater than 110 pixels, it is estimated that the distance between the target user and the image acquisition device is less than 30 cm. At this time, the iris area in the face image is relatively clear, that is, the influence of low resolution factors is small. The iris can be determined as the second preset part of the human face. When the imaging width of the face in the face image is less than 110 pixels, it is estimated that the distance between the target user and the image acquisition device is greater than 30 cm. At this time, the iris area in the face image is not clear, that is, the low resolution factor has a greater impact. The face can be determined as the second preset part of the human face.

In one embodiment, a second threshold and a third threshold may be preset for the imaging width of the face, and the second threshold is greater than the third threshold. Step S830 may include:

When the imaging width of the face in the face image is greater than the second threshold, the iris is determined as the second preset part of the face;

When the imaging width of the face in the face image is less than the second threshold and greater than the third threshold, the pupil is determined as the second preset part of the face;

When the imaging width of the face in the face image is smaller than the third threshold, the face is determined as the second preset part of the face.

Wherein, the second threshold and the third threshold may be determined according to experience and parameters of the image acquisition device. It can be seen that as the influence of the low-resolution factor decreases, a smaller preset face part tends to be used as the second preset face part.

It should be noted that, the present disclosure does not limit the number of preset parts of the second human face.

Step S840: Determine the distance between the target user and the image acquisition device according to the imaging size of the second preset part of the face in the face image.

The distance between the target user and the image acquisition device can be calculated according to the relationship of similar triangles with reference to the above-mentioned FIG. 6 and related contents.

When multiple second preset parts of the human face are selected, the distance can be determined in combination with the imaging sizes of the multiple second preset parts of the human face with reference to the relevant content in step S330.

Based on the method shown in Figure 8, on the one hand, the distance between the target user and the image acquisition device is preliminarily estimated through the first preset part of the face, so as to determine a suitable second preset part of the face according to actual factors, and then according to The imaging size of the second preset part of the face finally determines the distance between the target user and the image acquisition device, which can reduce the impact of the imaging instability of a single preset part of the face, and the face image is affected by the environment such as light The influence of conditions is small, which is beneficial to improve the accuracy of distance detection. On the other hand, this solution can be realized based on image acquisition devices such as cameras, without special configuration of distance sensors, and has low hardware cost, which is especially suitable for deployment in mobile scenarios such as mobile phones.

In one embodiment, the distance detection method shown in FIG. 8 can be implemented through the process shown in FIG. 9, including:

Step S910, input a face image, the face image is the face image of the target user collected by the image acquisition device;

Step S920, detecting the key points of the human face, using the face as the first preset part of the human face;

Step S930, determining the imaging width of the face;

Step S940, judging whether the imaging width of the face is greater than the first threshold, if yes, execute step S950, if not, execute step S960;

Step S950, using the iris as the preset part of the second face to detect the iris, and continue to execute step S970;

Step S960, taking the face as the preset part of the second human face, and proceed to step S970;

Step S970, determining the imaging size of the preset part of the second face;

Step S980: Determine the distance between the target user and the image acquisition device according to the imaging size of the preset part of the second face. The process ends.

Exemplary embodiments of the present disclosure also provide a control method. Referring to Fig. 10, the control method may include the following steps S1010 and S1020:

Step S1010, acquiring the distance between the target user and the image acquisition device, which is detected according to the distance detection method in this exemplary embodiment;

Step S1020, generating a corresponding control instruction according to the above distance.

Wherein, the control instruction may be an instruction in any aspect, such as a control instruction for a display screen of an electronic device, or a control instruction for a currently running application program. Generally, control instructions corresponding to a specific distance or distance range may be pre-configured, and then when it is detected that the distance satisfies the configured distance or distance range during operation, the corresponding control instruction is triggered to be generated and executed. Exemplarily, when the distance between the target user and the image acquisition device is less than 20cm, a control instruction for presenting prompt information may be generated, and the prompt information is used to prompt the user to pay attention to the distance of the mobile phone and protect the eyes, which may be text or voice information; when the target When the distance between the user and the image acquisition device is greater than 40 cm, a control instruction for keeping the screen off may be generated to control the electronic device to enter the screen-off state.

In an implementation manner, control instructions corresponding to a specific distance or distance range in a specific scenario may also be pre-configured. The specific scenario may be running a specific application program, the electronic device is in a specific operating state, and the like. Thus, in step S1020, a corresponding control command may be generated according to the above distance and the current operating scene of the electronic device. For example, in the scene of playing video, when the distance between the target user and the image acquisition device is less than 20cm, a control command to present the above prompt information can be generated; Next, when the distance between the target user and the image acquisition device is greater than 40cm, a control instruction for the screen can be generated.

Based on the method shown in FIG. 10 , corresponding control instructions can be executed according to the distance between the user and the device, realizing automatic and intelligent control, reducing user operations and improving user experience.

Exemplary embodiments of the present disclosure also provide a distance detection device. Referring to FIG. 11 , the distance detecting device 1100 may include a processor 1110 and a memory 1120 . Memory 1120 includes the following program modules:

The image acquisition module 1121 is configured to acquire the face image of the target user collected by the image acquisition device;

The imaging size determination module 1122 is configured to determine the imaging sizes of at least two preset parts of the face in the face image;

The distance determination module 1123 is configured to determine the distance between the target user and the image acquisition device according to the imaging sizes of the above-mentioned at least two preset parts of the face;

The processor 1110 is used to execute the above program modules.

Exemplary embodiments of the present disclosure also provide another distance detection device. Referring to Figure 12, the distance detection device 1200 may include:

The image acquisition module 1210 is configured to acquire the face image of the target user collected by the image acquisition device;

The imaging size determination module 1220 is configured to determine the imaging sizes of at least two preset parts of the face in the face image;

The distance determination module 1230 is configured to determine the distance between the target user and the image acquisition device according to the imaging sizes of the above-mentioned at least two preset parts of the face.

In one embodiment, the determination of the imaging sizes of at least two preset parts of the face in the face image includes:

By detecting the key points of the face in the face image, to determine the preset part of the face in the face image;

The imaging size of the preset part of the face is determined according to the pixels covered by the preset part of the face in the face image.

In one embodiment, the above-mentioned detection of key points of the face in the face image, and determining the preset position of the face in the face image include:

Detect the key points of the face in the face image, including the key points of the face contour and the key points of the eyes;

In one embodiment, when the preset part of the face includes a face, determining the imaging size of the preset part of the face according to the pixels covered by the preset part of the face in the face image includes:

In one embodiment, when the preset part of the face includes a face, the above-mentioned determining the imaging size of the preset part of the face according to the pixels covered by the preset part of the face in the face image further includes:

According to the pixel points covered by the face in the face image, the symmetry axis of the face is determined, and the vertical direction of the symmetry axis of the face is taken as the direction of the preset coordinate axis.

In one embodiment, when the preset part of the face includes the iris, determining the imaging size of the preset part of the face according to the pixels covered by the preset part of the face in the face image includes:

Determine the imaging area of the iris according to the number of pixels covered by the iris in the face image;

In one embodiment, when the preset part of the face includes the pupil, the above-mentioned determining the imaging size of the preset part of the face according to the pixels covered by the preset part of the face in the face image includes:

Determining the center point of the left pupil and the center point of the right pupil according to the pixel points covered by the left pupil and the right pupil respectively in the face image;

The distance between the center point of the left pupil and the center point of the right pupil is determined to obtain the imaging distance of the pupils.

In one embodiment, the predetermined parts of the human face include the face and the iris, and the above-mentioned determination of the imaging sizes of at least two preset parts of the human face in the human face image includes:

Determining the imaging width of the face in the face image;

In one embodiment, the predetermined parts of the human face include the face and the pupil, and the above-mentioned determination of the imaging sizes of at least two preset parts of the human face in the human face image includes:

Determining the imaging width of the face in the face image;

determining a second size range for the iris according to the imaging width of the face and the second scale range;

In one embodiment, the determination of the distance between the target user and the image acquisition device based on the imaging sizes of the at least two preset parts of the face includes:

Determine the candidate distance between the target user and the image acquisition device according to the ratio of the actual size of each preset part of the face to the imaging size and the imaging parameters of the image acquisition device;

In one embodiment, the above-mentioned candidate distance corresponding to the imaging size of each preset part of the face is used to determine the distance between the target user and the image acquisition device, including:

Based on the weight of each preset face part, the candidate distance corresponding to the imaging size of each preset face part is weighted to obtain the distance between the target user and the image acquisition device.

In one embodiment, the preset parts of the face include the face and the iris, and the imaging size of the at least one preset part of the face includes the imaging width of the face; Or at least one candidate distance to determine the weight of each preset part of the face, including:

The weight of the face and the weight of the iris are determined by the following formula:

Among them, _wiris represents the weight of the iris, w _face represents the weight of the face; e1 represents the linear coefficient; d _face represents the imaging width of the face.

Exemplary embodiments of the present disclosure also provide another distance detection device. Referring to FIG. 13 , the distance detecting device 1300 may include a processor 1310 and a memory 1320 . Memory 1320 includes the following program modules:

The image acquisition module 1321 is configured to acquire the face image of the target user collected by the image acquisition device;

The first preset human face part determination module 1322 is configured to determine at least one first preset human face part among the preset human face parts in the face image;

The second preset human face part determination module 1323 is configured to determine at least one second human face in the preset human face parts in the human face image according to the imaging size of the first preset human face part in the human face image preset position;

The distance determination module 1324 is configured to determine the distance between the target user and the image acquisition device according to the imaging size of the second preset part of the face in the face image;

The processor 1310 is used to execute the above program modules.

Exemplary embodiments of the present disclosure also provide another distance detection device. Referring to Figure 14, the distance detection device 1400 may include:

The image acquisition module 1410 is configured to acquire the face image of the target user collected by the image acquisition device;

The first preset human face part determination module 1420 is configured to determine at least one first preset human face part among the preset human face parts in the face image;

The second preset human face part determination module 1430 is configured to determine at least one second human face in the preset human face parts in the human face image according to the imaging size of the first preset human face part in the human face image preset position;

The distance determination module 1440 is configured to determine the distance between the target user and the image acquisition device according to the imaging size of the second preset part of the face in the face image.

In an implementation manner, the first predetermined face part includes a face. According to the imaging size of the first preset part of the face in the face image, at least one second preset part of the face is determined in the preset parts of the face in the face image, including:

Exemplary embodiments of the present disclosure also provide a control device. Referring to FIG. 15 , the control device 1500 may include a processor 1510 and a memory 1520 . Memory 1520 includes the following program modules:

The distance acquisition module 1521 is configured to acquire the distance between the target user and the image acquisition device, which is detected according to the distance detection method in this exemplary embodiment;

The control instruction generation module 1522 is configured to generate a corresponding control instruction according to the distance;

The processor 1510 is used to execute the above program modules.

Exemplary embodiments of the present disclosure also provide another control device. Referring to FIG. 16, the control device 1600 may include:

The distance acquisition module 1610 is configured to acquire the distance between the target user and the image acquisition device, which is detected according to the distance detection method in this exemplary embodiment;

The control instruction generation module 1620 is configured to generate a corresponding control instruction according to the above distance.

The specific details of each part of the above-mentioned device have been described in detail in the implementation of the method, and details that are not disclosed can be found in the implementation of the method, so details are not repeated here.

Exemplary embodiments of the present disclosure also provide a computer-readable storage medium, which can be realized in the form of a program product, which includes program code, and when the program product is run on the electronic device, the program code is used to make the electronic device The device executes (more specifically, causes the processor of the electronic device to execute) the steps of the various exemplary embodiments described in the "Exemplary Methods" section above in this specification.

In one embodiment, the program product can be implemented as a portable compact disk read only memory (CD-ROM) and include program code, and can run on an electronic device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, apparatus or device.

A program product may take the form of any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium includes, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, CD-ROM, optical storage device, magnetic storage device, or any suitable combination of the above.

A computer readable signal medium may include a data signal carrying readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming Language - such as "C" or similar programming language. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server to execute. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider). business to connect via the Internet).

It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. Actually, according to the exemplary embodiment of the present disclosure, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided to be embodied by a plurality of modules or units.

Those skilled in the art can understand that various aspects of the present disclosure can be implemented as a system, method or program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which can be collectively referred to herein as "circuit", "module" or "system". Other embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, and these modifications, uses or adaptations follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not disclosed in the present disclosure . The specification and embodiments are to be considered as exemplary only, with the true scope and spirit of the disclosure indicated by the appended claims.

It should be understood that the present disclosure is not limited to the precise constructions which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

A distance detection method, characterized in that, comprising:

Obtaining the face image of the target user collected by the image collection device;

determining the imaging sizes of at least two preset parts of the face in the face image;

The distance between the target user and the image acquisition device is determined according to the imaging sizes of the at least two preset parts of the face.
The method according to claim 1, wherein the determining the imaging sizes of at least two preset parts of the face in the face image comprises:

Detecting the key points of the human face in the human face image, and determining the preset position of the human face in the human face image;

The imaging size of the preset part of the face is determined according to the pixels covered by the preset part of the face in the face image.
The method according to claim 2, wherein the detecting the key points of the human face in the human face image and determining the preset position of the human face in the human face image comprises:

Detecting human face key points in the human face image, the human face key points include facial contour key points and eye key points;

Determining the face in the face image according to the key points of the face contour;

Intercepting an eye image from the human face image based on the eye key points, and detecting iris key points and/or pupil key points in the eye image to determine the iris and/or pupil key points in the human face image or pupils.
The method according to claim 2, wherein when the preset part of the human face includes a face, determining according to the pixels covered by the preset part of the human face in the face image The imaging size of the predetermined part of the face includes:

In the pixel points covered by the face in the face image, obtain the minimum coordinate value and the maximum coordinate value along the direction of the preset coordinate axis, and determine the face according to the minimum coordinate value and the maximum coordinate value image width.
The method according to claim 4, wherein when the preset part of the human face includes a face, determining according to the pixels covered by the preset part of the human face in the face image The imaging size of the predetermined part of the face also includes:

A face symmetry axis is determined according to the pixels covered by the face in the human face image, and the vertical direction of the face symmetry axis is used as the preset coordinate axis direction.
The method according to claim 2, wherein when the preset part of the human face includes an iris, the determined according to the pixels covered by the preset part of the human face in the face image Describe the imaging size of the preset parts of the face, including:

determining the imaging area of the iris according to the number of pixels covered by the iris in the face image;

The imaging diameter of the iris is determined according to the imaging area of the iris.
The method according to claim 2, wherein when the preset part of the human face includes pupils, the determined according to the pixels covered by the preset part of the human face in the face image Describe the imaging size of the preset parts of the face, including:

Determining the center point of the left pupil and the center point of the right pupil respectively according to the pixel points covered by the left pupil and the right pupil in the face image;

Determining the distance between the center point of the left pupil and the center point of the right pupil to obtain the imaging distance of the pupils.
The method according to claim 1, wherein the preset parts of the human face include the face and the iris, and determining the imaging sizes of at least two preset parts of the human face in the face image comprises:

determining the imaging width of the face in the face image;

determining a first size range for the iris according to the imaging width of the face and the first scale range;

Determine the imaging diameter of the iris in the face image, and determine that the imaging diameter is valid if the imaging diameter is within the first size range.
The method according to claim 1, wherein the preset parts of the human face include the face and pupils, and determining the imaging sizes of at least two preset parts of the human face in the human face image includes:

determining the imaging width of the face in the face image;

determining a second size range for the iris according to the imaging width of the face and the second scale range;

Determine the imaging distance of the pupils in the face image, and determine that the imaging distance is valid if the imaging distance is within the second size range.
The method according to claim 1, wherein the determining the distance between the target user and the image acquisition device according to the imaging sizes of the at least two preset parts of the face comprises:

Determine the candidate distance between the target user and the image acquisition device according to the ratio of the actual size of each preset part of the face to the imaging size and the imaging parameters of the image acquisition device;

Based on the candidate distances corresponding to the imaging sizes of each preset part of the face, the distance between the target user and the image acquisition device is determined.
The method according to claim 10, wherein the distance between the target user and the image acquisition device is determined based on the candidate distance corresponding to the imaging size of each preset part of the face ,include:

determining the weight of each preset part of the face according to the imaging size of at least one preset part of the face or at least one of the candidate distances;

Based on the weight of each preset part of the face, the candidate distance corresponding to the imaging size of each preset part of the face is weighted to obtain the distance between the target user and the image acquisition device. distance.
The method according to claim 10, wherein the predetermined part of the human face comprises the face and the iris, and at least one imaging size of the predetermined part of the human face comprises the imaging width of the face; An imaging size of the preset part of the human face or at least one of the candidate distances, determining the weight of each preset part of the human face, including:

The weight of the face and the weight of the iris are determined by the following formula:

Among them, wiris represents the weight of the iris, w face represents the weight of the face; e1 represents the linear coefficient; d face represents the imaging width of the face.
A distance detection method, characterized in that, comprising:

Obtaining the face image of the target user collected by the image collection device;

Determining at least one first preset face part in the preset face part in the face image;

According to the imaging size of the first predetermined face part in the face image, at least one second preset part of the face is determined among the preset parts of the face in the face image;

The distance between the target user and the image acquisition device is determined according to the imaging size of the second preset part of the human face in the human face image.
The method according to claim 13, wherein the first preset part of the human face comprises a face; and according to the imaging size of the first preset part of the human face in the face image, in the Determining at least one second preset part of the face in the preset part of the face in the face image, including:

When the imaging width of the face in the face image is greater than a first threshold, the iris in the face image is determined as a second preset part of the face;

When the imaging width of the face in the face image is smaller than the first threshold, the face is determined as a second preset part of the face.
A control method, characterized in that, comprising:

Obtaining the distance between the target user and the image acquisition device, the distance is detected according to the distance detection method described in any one of claims 1 to 14;

Generate corresponding control instructions according to the distance.
A distance detection device is characterized in that it includes a processor and a memory, and the processor is used to execute the following program modules stored in the memory:

The image acquisition module is configured to acquire the face image of the target user collected by the image acquisition device;

The imaging size determination module is configured to determine the imaging sizes of at least two preset parts of the face in the face image;

The distance determination module is configured to determine the distance between the target user and the image acquisition device according to the imaging sizes of the at least two preset parts of the face.
A distance detection device is characterized in that it includes a processor and a memory, and the processor is used to execute the following program modules stored in the memory:

The image acquisition module is configured to acquire the face image of the target user collected by the image acquisition device;

The first preset human face part determination module is configured to determine at least one first preset human face part among the preset human face parts in the face image;

The second predetermined face part determination module is configured to determine at least one preset part of the face in the face image according to the imaging size of the first preset part of the face in the face image A second preset part of the face;

The distance determination module is configured to determine the distance between the target user and the image acquisition device according to the imaging size of the second preset part of the face in the face image.
A control device, characterized in that it includes a processor and a memory, the processor is used to execute the following program modules stored in the memory:

The distance acquisition module is configured to acquire the distance between the target user and the image acquisition device, the distance is detected according to the distance detection method according to any one of claims 1 to 14;

A control instruction generation module configured to generate a corresponding control instruction according to the distance.
A computer-readable storage medium on which a computer program is stored, wherein the computer program implements the method according to any one of claims 1 to 15 when executed by a processor.
An electronic device, characterized in that it comprises:

processor; and

a memory for storing executable instructions of the processor;

Wherein, the processor is configured to execute the method according to any one of claims 1 to 15 by executing the executable instructions.