CN110175518B

CN110175518B - Camera angle adjusting method, device, equipment and system of camera device

Info

Publication number: CN110175518B
Application number: CN201910320365.5A
Authority: CN
Inventors: 李旭
Original assignee: Advanced New Technologies Co Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2019-04-19
Filing date: 2019-04-19
Publication date: 2023-02-28
Anticipated expiration: 2039-04-19
Also published as: CN116132786A; CN110175518A

Abstract

The embodiment of the specification provides a camera angle adjusting method, a camera angle adjusting device, camera angle adjusting equipment and a camera angle adjusting system of a camera device.

Description

Camera angle adjusting method, device, equipment and system of camera device

Technical Field

The present disclosure relates to the field of control technologies, and in particular, to a method, an apparatus, a device, and a system for adjusting a camera angle of an imaging apparatus.

Background

For the equipment applying face recognition, besides the accuracy and safety requirements of a face recognition software algorithm, the angle of a camera on the equipment has a great influence on the passing rate of the face recognition, and the angle of the camera directly influences the first link of the face recognition, namely the face data acquisition stage. How to collect a face image with higher quality is one of the important links in the whole link of face recognition. For the offline human face recognition terminal, the height and the shooting angle of the camera are often configured in a unified manner, however, people in different regions may have height differences, and therefore, human face images of some people may not be acquired through the uniformly configured camera, or a user needs to bend over or pad feet to enable the face to fall into the acquisition range of the camera.

Disclosure of Invention

In order to overcome the problems in the related art, the present specification provides a camera angle adjustment method, device, apparatus, and system for an image pickup device.

According to a first aspect of embodiments of the present specification, there is provided a method for adjusting an angle of a camera device, where the camera device includes a support and a camera, the camera is movably connected to the support, and the camera device is configured to acquire a face image, and the method includes:

acquiring position information of a face in an image, wherein the image comprises an image acquired by a camera device at an existing initial shooting angle;

calculating a correction shooting angle of the camera according to the position information of the face in the image;

and controlling the supporting part to adjust the shooting angle of the camera to the corrected initial shooting angle according to the corrected shooting angle.

In one embodiment, the image includes at least: and correcting the initial shooting angle last time and then acquiring an image by the camera device during the current time.

In one embodiment, a face recognition device connected to the camera device is used for performing face recognition on an image acquired by the camera device, and determining position information of a face in the image during the recognition process, wherein the position information of the face in the image is acquired from the face recognition device and recorded.

In one embodiment, the acquiring the position information of the human face in the image includes: when the preset adjusting condition is met, acquiring the position information of the face in the image;

the preset adjusting condition comprises one or more of the following conditions:

the face recognition failure times reach a preset failure time threshold;

the preset angle adjustment time is up;

and carrying out face recognition on the image acquired by the camera device.

In one embodiment, the method further comprises:

when the camera device is started for the first time, acquiring the height of a camera in the camera device from the ground, the preset crowd height range, the average length of a human face and the distance between a person and a vertical plane where the camera is located, and determining the initial shooting angle of the camera;

and controlling the supporting part to adjust the shooting angle of the camera to the initial shooting angle.

In one embodiment, the method further comprises:

acquiring an image acquired by a camera device in a preset camera test mode;

if the face exists in the image and the face is in the designated area in the image, outputting prompt information of successful test; or the like, or a combination thereof,

if a part of human face exists in the image, determining an adjusting direction according to the position of the human face in the image, and controlling a supporting part to finely adjust the shooting angle of the camera according to a first preset angle step length along the adjusting direction; if the adjusted camera device collects images containing complete faces, the current shooting angle of the camera is used for updating the existing initial shooting angle; or the like, or a combination thereof,

if the face does not exist in the image, controlling the support part to adjust the shooting angle of the camera according to a second preset angle step length along a preset adjustment direction so that the face in the image acquired by the camera device is within a specified area range in the image, and if the face in the image acquired by the camera device is within the specified area range in the image, updating the existing initial shooting angle by using the current shooting angle of the camera; and outputting early warning information if the adjusting times reach a preset time threshold.

In one embodiment, the method further comprises:

acquiring an image currently acquired by a camera device;

when the image does not have a complete face, the supporting part is controlled to adjust the shooting angle of the camera according to the position information of the face in the image, so that the camera device acquires the image containing the face of the current photographed person.

In one embodiment, the acquiring an image currently acquired by a camera includes: and acquiring the image currently acquired by the camera device after the interval of the wakeup start of the camera device is appointed.

In one embodiment, the method further comprises: and after the face recognition is finished, the control supporting part adjusts the shooting angle of the camera back to the initial shooting angle.

According to a second aspect of the embodiments of the present specification, there is provided a camera angle adjusting device of a camera device, the camera device includes a support and a camera, the camera is movably connected to the support, the camera device is used for collecting a face image, the camera angle adjusting device of the camera device includes:

an information acquisition module to: acquiring position information of a face in an image, wherein the image comprises an image acquired by a camera device at an existing initial shooting angle;

an angle correction module to: calculating a correction shooting angle of the camera according to the position information of the face in the image;

an angle adjustment module to: and controlling the supporting part to adjust the shooting angle of the camera to the corrected initial shooting angle according to the corrected shooting angle.

In one embodiment, the image includes at least: and correcting the initial shooting angle last time and then acquiring the image by the camera device during the current time.

In one embodiment, the information obtaining module is configured to: when the preset adjusting condition is met, acquiring the position information of the face in the image;

the face recognition failure times reach a preset failure time threshold;

the preset angle adjustment time is reached;

and carrying out face recognition on the image acquired by the camera device.

In one embodiment, the apparatus further comprises an angle initialization module to:

when the camera device is started for the first time, the height of a camera in the camera device from the ground, the preset crowd height range, the average length of a human face and the distance between a person and the vertical plane where the camera is located are obtained, and the initial shooting angle of the camera is determined;

In one embodiment, the apparatus further comprises a testing module to:

acquiring an image acquired by a camera device in a preset camera test mode;

if a part of human face exists in the image, determining an adjusting direction according to the position of the human face in the image, and controlling a supporting part to finely adjust the shooting angle of the camera according to a first preset angle step length along the adjusting direction; if the adjusted camera device acquires an image containing a complete face, updating the existing initial shooting angle by using the current shooting angle of the camera; or the like, or a combination thereof,

In one embodiment, the apparatus further comprises a real-time adjustment module to:

acquiring an image currently acquired by a camera device;

In one embodiment, the acquiring, by the real-time adjusting module, an image currently acquired by a camera includes: and acquiring the image currently acquired by the camera device after the interval of the wakeup start of the camera device is appointed.

In one embodiment, the real-time adjustment module is further configured to: and after the face recognition is finished, the control supporting part adjusts the shooting angle of the camera back to the initial shooting angle.

According to a third aspect of embodiments herein, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method as described above when executing the program.

According to a fourth aspect of the embodiments of the present specification, there is provided a face recognition system, including a face recognition terminal, a face recognition server, and an angle adjustment device; the face recognition terminal comprises a camera device for collecting a face image, the camera device comprises a supporting part and a camera, and the camera is movably connected to the supporting part; the face recognition server is used for carrying out face recognition on a face image collected by the face recognition terminal;

the angle adjustment device is used for:

The technical scheme provided by the embodiment of the specification can have the following beneficial effects:

in the embodiment, by acquiring the position information of the face in the image, because the image includes the image acquired by the camera device at the existing initial shooting angle, the corrected shooting angle of the camera can be calculated according to the position information of the face in the image, and the support part is controlled according to the corrected shooting angle to adjust the shooting angle of the camera to the corrected initial shooting angle, so that the shooting angle of the camera can be automatically adjusted, and the adjusted camera can acquire the face images of most people in the area.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the specification.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present specification and together with the description, serve to explain the principles of the specification.

Fig. 1 is a view illustrating an application scenario of a camera angle adjustment method of an image capturing apparatus according to an exemplary embodiment.

Fig. 2 is a flowchart illustrating a camera angle adjustment method of an image capturing apparatus according to an exemplary embodiment.

Fig. 3A is a schematic diagram illustrating a user-camera position relationship according to an exemplary embodiment.

Fig. 3B is a schematic diagram illustrating a determination of a photographing angle according to an exemplary embodiment of the present description.

Fig. 4 is a schematic diagram illustrating a photographing angle adjusting method according to an exemplary embodiment of the present disclosure.

Fig. 5 is a hardware configuration diagram of a computer device in which a camera angle adjustment device of an image pickup apparatus according to an exemplary embodiment is shown in the present specification.

Fig. 6 is a block diagram of a camera angle adjustment apparatus of an image pickup apparatus shown in the present specification according to an exemplary embodiment.

FIG. 7 is a block diagram of a face recognition system shown in accordance with an exemplary embodiment of the present description.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with this description. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the specification, as detailed in the claims that follow.

The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the description. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of the present specification. The word "if" as used herein may be interpreted as "at" \8230; "or" when 8230; \8230; "or" in response to a determination ", depending on the context.

Applicants have discovered that population height is a regional and regional characteristic, such as the height of the southern population may be generally lower than the height of the northern population, and the height of the elementary and secondary school students may be generally lower than the height of adults. The cameras in different cities or different regions are all configured with the same shooting angle, and the face images of some people can not be collected by the cameras with uniformly configured shooting angles. For example, in a store near a middle and primary school, more students brush their faces to perform identity authentication, and less adults brush their faces to perform identity authentication, and if a shooting angle suitable for the height of an adult is adopted, face images of most people cannot be acquired through a camera.

Therefore, the embodiment of the present specification provides a camera angle adjusting method for a camera device, which can automatically adjust a shooting angle of a camera, so that the adjusted camera can acquire face images of most people in the area.

The method for adjusting the angle of the camera of the image capturing apparatus provided in this embodiment may be implemented by software, or may be implemented by combining software and hardware, or by hardware, where the hardware may be composed of two or more physical entities, or may be composed of one physical entity. The method of the embodiment can be applied to electronic equipment. The electronic device may be a tablet computer, a notebook computer, a desktop computer, a PDA (Personal Digital Assistant), and the like.

The embodiment of the invention can be applied to a face recognition scene, such as a scene of identity verification based on face recognition. In a face recognition scene, a camera device, a face recognition device and an angle adjusting device can be involved. The angle adjustment apparatus may be used to perform a camera angle adjustment method of the image pickup apparatus. The camera device comprises a supporting part and a camera, and the camera is movably connected to the supporting part. The face recognition device is used for carrying out face recognition on the image collected by the camera device. Face recognition devices are often used for authentication. In one example, based on the requirement of the recognition speed and the support of the hardware device, the camera device and the face recognition device may be disposed in the same terminal, and the terminal may be disposed in an online scene, such as an online shop, a shopping mall, or other places with face recognition requirements. In another example, the camera and the face recognition device are different devices, and the camera is set in an off-line scene, such as an off-line face recognition terminal. The face recognition terminal may include a camera and a display screen. The face recognition means may be provided in a background server. Correspondingly, the angle adjusting device and the face recognition device can be arranged in the same equipment or not, and can be configured according to requirements.

In one embodiment, one of the application scenarios is illustrated. Fig. 1 is a view of an application scenario of a camera angle adjustment method of an image capturing apparatus according to an exemplary embodiment. In the application scene, the system can comprise an angle adjusting device, a face recognition server and a face recognition terminal, wherein the angle adjusting device and the face recognition server can be configured on different devices, a camera device is configured on the face recognition terminal, and the face recognition terminal can further comprise a display screen to display the collected face images. The face recognition terminal can be arranged in places with face recognition requirements, such as shops, shopping malls, subways and the like on line.

The camera device provided by the embodiment of the invention can be used for collecting the face image in an offline scene. The camera device comprises a camera and a supporting part, the camera is movably connected to the supporting part, and the supporting part is used for adjusting the shooting angle of the camera. For example, the support may be a motorized pan and tilt head. The electric pan-tilt can enlarge the monitoring range of the camera. The electric cradle head can receive signals from the controller to accurately operate and position. Under the effect of control signal, the camera on the cloud platform can adjust and shoot the angle.

As shown in fig. 2, which is a flowchart illustrating a camera angle adjusting method of a camera device according to an exemplary embodiment of the present specification, the camera device includes a support and a camera, the camera is movably connected to the support, the camera device is configured to capture a face image, and the method includes:

in step 202, position information of a human face in an image is acquired, wherein the image is acquired by a camera device;

in step 204, calculating a corrected shooting angle of the camera according to the position information of the face in the image;

in step 206, the supporting part is controlled to adjust the shooting angle of the camera to the corrected initial shooting angle according to the corrected shooting angle.

With respect to the image, the image is captured by the camera, and the image includes, for example, an image captured by the camera at an existing initial shooting angle. The number of images may be one or more. The position information of the face in the image is data for assisting the adjustment of the shooting angle. Therefore, the larger the data amount of the image to be referred to, the more accurate the correction result is obtained. Also, to improve the accuracy of the correction result, the image may be an image acquired at the latest period of time, such as acquiring a plurality of images in time sequence. In one example, the image includes at least: and correcting the initial shooting angle last time and then acquiring the image by the camera device during the current time. At least the face position information in the image acquired at present after the last correction is used as a reference factor for correcting the initial shooting angle, so that the correction accuracy can be improved. For example, each time an image is obtained, the position information of a human face in the image may be recorded. Step 202 may obtain location information of a face in an image from a history.

The position information of the face in the image may be position information of the face in the image, for example, a face region in the image is determined by using a face positioning method, so as to obtain the position information of the face. And taking the position of the face in the image as an adjustment basis, calculating a corrected shooting angle of the camera, and controlling the supporting part to adjust the shooting angle of the camera to the corrected initial shooting angle according to the corrected shooting angle so as to obtain a shooting angle suitable for the height of local user groups.

Regarding the position information of the human face, in one example, the image may be directly obtained from the camera device, and the execution end obtains the position information of the human face in the image by detecting the position of the human face in the image. After each recognition, the position information of the face is identified and stored in the database.

In another example, the image may be an image of a face recognition device performing face recognition, and since the face recognition device performs face position detection when performing face recognition according to the image, the position information of the face in the image may be acquired and recorded from the face recognition device, for example, after the face recognition device completes recognition operation each time, the position information of the face in the image may be sent to the execution end, or the execution end actively acquires the position information of the face from the face recognition device. After the execution end obtains the position information of the face in the image, the position information of the face can be recorded. In the embodiment, the position information of the face is directly acquired from the face recognition device, so that the waste of resources for calculating the position information of the face can be avoided. The face recognition device is connected with the camera device and used for carrying out face recognition on the image collected by the camera device. The face recognition device can be a functional module for realizing face recognition.

Regarding the acquisition timing of the position information of the human face, in one embodiment, the acquiring the position information of the human face in the image includes: and when the preset adjustment condition is met, acquiring the position information of the face in the image. The preset adjustment condition may be a condition that is set in advance to trigger adjustment of the photographing angle. Illustratively, the preset adjustment condition includes one or more of the following conditions:

the face recognition failure times reach a preset failure time threshold;

the preset angle adjustment time is reached;

and carrying out face recognition on the image acquired by the camera device.

The face recognition failure may be caused by that no image including a face is acquired, for example, a shooting area of a camera does not cover a face area of a photographed person; it may also be caused by the difficulty in recognizing the face of the photographed object itself. Therefore, a preset failure time threshold is set, the preset failure time threshold can be larger than 2, and shooting angle adjustment is triggered after multiple failures. The preset failure time threshold may also be configured in combination with the requirement for identification accuracy, which is not listed here. In this embodiment, when the face recognition failure number reaches the preset number threshold, the steps 202 to 206 are triggered to be executed, so as to adjust the shooting angle of the camera.

The preset angle adjusting time may be a preset time for adjusting the shooting angle. The preset angle adjustment time may be a certain time of an idle period, and the idle period may be a period in which the number of objects to be recognized appearing before the image pickup device is small. For example, in the range of 1. For example, the preset angle adjustment time may be 2. The designated period of the preset angle adjustment time can also be flexibly adjusted, for example, when the number of times of acquiring images not including a face reaches the preset number of times, or the number of times of face recognition failure reaches the preset failure number threshold, and the like, the designated period of the preset angle adjustment time can be shortened, for example, if the current period is one week, and if the number of times of acquiring images not including a face reaches the preset number of times, or the number of times of face recognition failure reaches the preset failure number threshold, the period of the preset angle adjustment time is updated to two days.

In another example, the preset adjustment condition may be that face recognition of an image captured by the camera is completed. The face recognition completion may include a face recognition success and a face recognition unsuccessful. In some scenes, the requirement on the shooting angle of the camera may be high, and the position of the camera can be adjusted by using the face position information in the image adopted by the face recognition after the face recognition is completed every time, so as to ensure that the next recognition can be completed correctly with high probability. Taking the identity authentication in payment by face recognition as an example, after face payment is completed each time, the position of the camera can be adjusted according to the recognition condition.

It is to be understood that the preset adjustment conditions described above may also be combined as long as there is no conflict. For example, the conditions: the face recognition failure times reach a preset failure time threshold, and the conditions are as follows: if any of the preset angle adjustment time reaches the combination and any of the conditions in the combination is satisfied, the execution of steps 202 to 206 is triggered. For another example, when the face recognition failure times reach a preset failure time threshold, the period of the angle adjustment time is adjusted, and the like. In addition, the preset adjustment condition includes, but is not limited to, the above condition, and may also be other conditions for triggering execution of shooting angle adjustment, which are not described herein any more.

After the position information of the face in the image is obtained, the corrected shooting angle of the camera can be calculated according to the position information of the face in the image.

As for the shooting angle, the shooting angle may be a horizontal angle and a pitch angle (vertical angle). In another example, since a human face is not shifted by a large left-right angle, it is generally within a shooting range of a camera, and a left-right shift easily causes other human faces to be recognized, and for this reason, only the pitch angle is corrected at a time.

The corrected shooting angle of the camera may be an angle change amount/an angle adjustment amount, and the shooting angle of the camera is adjusted to the corrected initial shooting angle by adjusting the camera set to the existing initial shooting angle by the corrected shooting angle.

According to the scheme of the embodiment, the probability that the camera shoots the image containing the face at the corrected initial shooting angle is higher than the probability that the camera shoots the image containing the face at the initial shooting angle before correction by correcting the existing initial shooting angle. In other words, the target of calculating the correction shooting angle may be: it is desirable that the probability that the camera captures an image including a human face at the corrected initial capturing angle (the capturing angle corrected in accordance with the corrected capturing angle) is greater than the probability that the camera captures an image including a human face at the initial capturing angle before correction.

For example, the probability that the camera shoots the image including the face at the corrected initial shooting angle is greater than the probability that the camera shoots the image including the face at the initial shooting angle before correction, and the prediction may be performed by using the position information of the face in all the acquired images. For example, for convenience of description, the face in the position information of the face in the image acquired in step 202 is defined as the face of the history user in the history user set. And calculating a corrected shooting angle according to whether the position information of all the faces designates a preferred area in the image and the preferred shooting area of the camera into which the faces fall is taken as a target, and realizing that the ratio of the number of historical users with the faces falling into the preferred shooting area to the number of users in the historical user set meets the requirement of a preset ratio or the number of the historical users with the faces falling into the preferred shooting area reaches a preset threshold value if the camera shoots at the corrected initial shooting angle. In this embodiment, the goal may be achieved by whether the ratio meets a preset ratio requirement/whether the quantity meets a quantity requirement: the probability that the camera shoots the image containing the face at the corrected initial shooting angle is greater than the probability that the camera shoots the image containing the face at the initial shooting angle before correction.

In one embodiment, the shooting angle correction calculation is performed according to all the obtained face position information, so as to ensure that the shooting range of the adjusted camera can cover the most existing faces in the record. In order to avoid the problem caused by large-range adjustment, each adjustment can be controlled within a range of plus or minus p degrees (such as 1 degree), and the shooting angle adjustment is performed when the ratio of the number of faces in the shooting range which can cover the record and corresponds to the newly calculated shooting angle to the total number of the faces in the record is greater than NUM/reaches a preset ratio threshold.

Taking the example of triggering and correcting the shooting angle at every specified interval period, at least recording the position information of the face in the image acquired by the camera device in the specified interval period, calculating the corrected shooting angle by taking the face in a preferred area (such as a middle area) of a shooting area as a target according to the position information of the face in the image and the shooting angle (the existing shooting angle) corresponding to the image when the specified interval period is set, controlling the supporting part according to the corrected shooting angle to adjust the shooting angle of the camera to the corrected initial shooting angle, and so on, wherein the data in each period can be used as the basis for adjusting the shooting angle, so that the adjusted shooting angle can be suitable for the height of the people suitable for the equipment. The embodiment can count the height characteristics of people using the face recognition terminal by using the initial value correction method, and adjust the optimal recognition angle of the camera, thereby ensuring that most users can be collected with face images.

The initial shooting angle set for the first time can be a default value, but in the carrying process, the angle can be changed, and the face angle cannot be aligned correctly. For this reason, the initial shooting angle of the camera can be adjusted and tested when the camera is installed. In one embodiment, the initial shooting angle of the camera is determined according to the type of the camera and the height of the camera in the camera from the ground. For example, the type of the camera device and the mapping relationship between the height of the camera head of the camera device from the ground and the initial shooting angle may be pre-stored, and after the type of the camera device and the height of the camera head of the camera device from the ground are obtained, the initial shooting angle may be determined. When the camera is started for angle adjustment for the first time, the initial shooting angle comprises a horizontal angle and a vertical angle.

In practical applications, the initial shooting angle obtained according to the type of the camera device and the height of the camera head on the ground in the camera device may be less related to the height of the local crowd, and for this reason, in another embodiment, the method further includes:

The height of the camera from the ground can be obtained by deducing the height of the upper edge of the screen of the face recognition terminal from the ground and the relative distance between the upper edge of the camera and the upper edge of the screen, and the height of the upper edge of the screen from the ground can be input by an installer during installation.

Regarding the preset crowd height range, in one embodiment, the preset crowd height range may be a height range determined according to the height of the face recognition terminal user in the area. For example, the height range may be input by the installer, or the height range of the crowd in the area acquired on the network. In another embodiment, the preset crowd height range may also be a preset general height range.

The average length of the face may be a preset value, for example, 27cm.

Regarding the distance between the person and the vertical plane where the camera is located, taking the camera as an example of being disposed on the plane where the screen is located, the distance between the person and the vertical plane where the camera is located may be the horizontal distance between the person and the screen, and therefore may be determined by the installation scene. The distance between the person and the vertical plane where the camera is located can be a specific value, can also be a range value, can be input by an installer, and can also be a default value.

For example, the area where the object to be recognized stands is specified on the spot, the distance of the person from the vertical plane where the camera is located can be determined. For another example, the distance range between the person and the vertical plane where the camera is located is obtained by inference according to the history. For example, the standing position of the user and the position of the camera in front of the desktop machine (face recognition terminal) are different from the horizontal distances between the standing position of the user and the camera in front of the vertical machine (face recognition terminal). The user habits of different crowds are different, and the actual distance between a person and the screen can be calculated by calculating the size of the face area occupying the screen. For example, when the face recognition terminal is started for the first time, an initial setting page can be provided, the manager can input information such as the height from the ground, the preset crowd height range, the average length of the face, the distance between a person and the vertical plane where the camera is located and the like on the screen, the machine can automatically calculate the initial horizontal/vertical angle of the camera, and the shooting angle can be adjusted through the electric holder.

Fig. 3A is a schematic diagram illustrating a position relationship between a user and a camera according to an exemplary embodiment. Fig. 3B is a schematic diagram illustrating a method for determining a photographing angle according to an exemplary embodiment. According to the upper limit value S in the crowd height range _max The height H of the camera from the ground and the horizontal distance L between a person and the screen determine an included angle alpha, for example,

according to the lower limit value S in the crowd height range _min The height H of the camera from the ground, the average length m of the face, and the horizontal distance L of the person from the screen determine an included angle β, for example,

therefore, the shooting angle of the camera can be determined according to (alpha-beta). In one example, the adjustment target of the shooting angle of the camera is: the shooting area of the camera can cover the area corresponding to the angle (alpha-beta). As an example, the photographing angle γ of the camera may be determined according to the median value of (α - β), for example,

correspondingly, the horizontal shooting angle can also be determined, which is not repeated herein.

It can be understood that other calculation formulas may also be used to determine the shooting angle of the camera, as long as the shooting area of the camera includes the area corresponding to the angle (α - β) as much as possible, which is not described herein again.

After the initial shooting angle of the camera is determined, in order to ensure the accuracy of adjustment, a camera test mode can be configured for a tester to test the shooting angle of the camera. The number of testers may be one or more. For example, it may be a tester that can represent the height characteristics of the population in the area. Illustratively, the method further comprises:

acquiring an image acquired by a camera device in a preset camera test mode;

if the face exists in the image and the face is in a designated area in the image, outputting prompt information of successful test; or the like, or a combination thereof,

if the image has a part of face, determining an adjusting direction according to the position of the face in the image, and controlling the supporting part to finely adjust the shooting angle of the camera according to a first preset angle step length along the adjusting direction; if the adjusted camera device acquires an image containing a complete face, updating the existing initial shooting angle by using the current shooting angle of the camera; or the like, or, alternatively,

For example, a camera test interface may be provided, and the tester looks at the camera, so that the camera can recognize whether the face range is within the shooting range of the camera.

The designated area may be a middle area of the image to indicate that the face is within a shooting range of the camera. If the face exists in the image and the face is in the designated area in the image, the shooting angle of the camera is appropriate, and the test is finished.

If the image has a part of human faces for indicating that only part of the human faces are in the shooting range of the camera, if the part of the human faces are in the upper limit or the lower limit of the shooting area, the adjusting direction can be determined according to the positions of the human faces in the image, and the supporting part is controlled to finely adjust the shooting angle of the camera along the adjusting direction according to the first preset angle step length. For example, if a human face appears in an upper area in the image, it means that the shooting range of the camera is expected to move upward, and therefore, the adjustment direction may be upward adjustment or the like. The first preset angle step may be set according to a requirement, for example, may be set to 1 degree, 5 degrees, and the like, and may specifically be determined according to a manner of an initial value calculated for the first time. For example, if the initial photographing angle is determined by the height of the camera from the ground, the preset crowd height range, the average length of the face, and the distance between the person and the vertical plane where the camera is located, the accuracy of the photographing angle of the camera is relatively high, and thus, the preset angle step may be set to a small angle, such as 1 degree. And if the adjusted camera device acquires an image containing a complete face, updating the existing initial shooting angle by using the current shooting angle of the camera.

And if the human face is not identified, controlling the supporting part to finely adjust the shooting angle of the camera according to a second preset angle step length along a preset adjusting direction so as to enable the human face in the image acquired by the camera device to be in a specified area range in the image. The preset adjusting direction may be a preset direction, and the preset adjusting direction is often more than one direction, and may be adjusted several times upwards and then downwards. The second preset angle step may be a preset larger angle value, for example, 10 degrees. For example, if no face is recognized, the camera is moved vertically and continuously downwards by 10 degrees, if no face is recognized, the camera is moved vertically and continuously upwards by 20 degrees, if the face is recognized after the angle is adjusted, the normal working state is entered, and if no face is recognized, the test is ended, and the pre-warning state can be entered.

In one embodiment, the second preset angle is updated according to the adjustment times or the adjustment time, so that the updated preset angle is larger than the preset angle before the update. For example, after adjusting twice or 10s, if the face is still not recognized, the second preset angle may be increased so that the face can be recognized as soon as possible.

The machine tool indicates that the current camera does not pass the verification at the warning stage, so that the fault risk exists, and the angle adjusting range during the identification is enlarged under the state; and if the human face is not recognized after s seconds from the beginning of the recognition, continuously moving the human face downwards for 20 degrees, and recognizing the human face in the moving process, if the human face is still not recognized, continuously moving the human face upwards for 40 degrees, if the human face is still not recognized, continuously moving the human face leftwards for 10 degrees, and if the human face is still not recognized, continuously moving the human face rightwards for 10 degrees. If the human face is still not recognized, the recognition fails.

In the testing process, if the continuous n-time identification is successful, the normal working state is entered, if the continuous m-time identification is failed, the alarm is given, otherwise, the state still returns to the pre-alarm state. After the machine enters the warning state, the face recognition identity authentication function (such as the face recognition payment function) is stopped, and a maintenance warning is sent to maintenance personnel.

In an embodiment, each time the camera is turned on, the current shooting angle of the camera may be compared with the stored initial shooting angle, and if the comparison fails, the camera may be adjusted to the stored initial shooting angle. If the comparison is successful, the normal working state can be entered.

In practical applications, a single higher or lower object to be recognized may occur, for example, an abnormal height object whose height is not within the height range of the local crowd may occur, and in order to perform face recognition for this special case, in one embodiment, a scheme for adjusting the shooting angle of the camera in real time is further provided. The method further comprises the following steps:

acquiring an image currently acquired by a camera device;

In this embodiment, after the image acquired by the camera device is obtained, the shooting angle of the camera can be adjusted step by step in real time according to whether a complete face exists in the image until the image including the face of the current photographed person is acquired by the camera device, so that the recognition module performs face recognition. The embodiment can dynamically adjust the shooting angle of the camera according to the use scene of the camera device, and realize the acquisition of the face image of the user with abnormal height.

The requirement on real-time performance is high during face recognition, and meanwhile, in the normal recognition process, the angle of a camera does not need to be adjusted in most cases, so that the situation that the user does not align the camera yet to cause recognition failure when recognition is started is considered, and therefore a delay adjustment strategy can be set. For example, the acquiring an image currently acquired by a camera includes: and acquiring the image currently acquired by the camera device after the interval of the wakeup start of the camera device is appointed. The designated time can be T, the T time is delayed, if qualified faces are not detected, adjustment is started, users with too high or too low heads are mainly dealt with during adjustment, and therefore the faces which are not originally in the shooting range corresponding to the initial shooting angle can be collected by adjusting the camera in real time.

For example, in the delay adjustment process, in order to ensure the recognition speed, a one-step adjustment strategy may be adopted, in which a first designated angle (e.g. 10 degrees) is adjusted downward once, and if no face is still recognized, a second designated angle (e.g. 20 degrees) is adjusted upward once again.

The embodiment can improve the recognition rate and reduce the error movement through the delay adjustment scheme.

Because the condition of triggering real-time adjustment is often a special condition, in view of this, after the shooting angle of the camera is adjusted in real time and face recognition is completed, the supporting part can be controlled to adjust the shooting angle of the camera back to the initial shooting angle, so as to ensure that the camera can acquire faces of most people.

Face recognition may be used for a variety of applications, for example, face recognition may be used for authentication. If the identity is verified according to the face recognition, payment is realized. For example, after face recognition is performed each time, if the face recognition fails, the face payment function is not directly quitted, but the user jumps to a terminal payment page according to personal information (such as a mobile phone number) input by the user, and prompt information of the failure in recognition is displayed on face brushing equipment, so that the problem that the two-dimensional code scanning process is performed again after the user fails in recognition is reduced.

The various technical features in the above embodiments can be arbitrarily combined, so long as there is no conflict or contradiction between the combinations of the features, but the combination is limited by the space and is not described one by one, and therefore, any combination of the various technical features in the above embodiments also belongs to the scope disclosed in the present specification.

One of the combinations is exemplified below.

Fig. 4 is a schematic diagram illustrating a photographing angle adjusting method according to an exemplary embodiment of the present disclosure. When an installer installs a face recognition terminal comprising a camera device, the type of the face recognition terminal and the height of the upper edge of a terminal screen from the ground are input. According to the embodiment, the initial horizontal/vertical shooting angle of the camera is obtained according to the type of the face recognition terminal and the height of the upper edge of the terminal screen from the ground, the angle is adjusted to be the initial horizontal/vertical shooting angle, and the angle is tested. The testing means is the same as that in the above embodiments, and is not described in detail here. And if the test fails, entering a warning stage. And in the warning stage, the collected images are identified, if the continuous identification is correct, the normal working state is entered, if the continuous identification fails, the warning state is entered, a warning prompt is sent, the camera is manually checked, or the warning state is still remained. The method can carry out self-checking when the mobile terminal is started every time, verify whether the current shooting angle is consistent with the initial shooting angle or not, and carry out automatic adjustment if the current shooting angle is inconsistent with the initial shooting angle. In normal work, in order to deal with users with abnormal height, fine adjustment of the vertical range can be carried out according to the currently detected face. And after the face recognition is finished, the control supporting part adjusts the shooting angle of the camera back to the initial shooting angle. When the preset adjusting condition is met, the position information of the face in the image is obtained, the corrected shooting angle of the camera is calculated according to the position information of the face in the image, and the support part is controlled according to the corrected shooting angle to adjust the shooting angle of the camera to the corrected initial shooting angle. The support part may be a motorized pan and tilt head or the like.

According to the embodiment, the supporting part is added, so that the camera in the face recognition terminal has the capability of automatically adjusting the angle, and the setting and detection of the initial position of the camera and the detection of the user with abnormal height are ensured. The initial value correction method can be used for counting the height characteristics of people using the terminal, adjusting the optimal recognition angle of the camera, and acquiring the face image of a user with abnormal height by adjusting the shooting angle in real time.

Corresponding to the embodiment of the camera angle adjusting method of the camera device, the specification also provides an embodiment of the camera angle adjusting device of the camera device and an electronic device applied by the camera angle adjusting device.

The embodiment of the camera angle adjusting device of the camera shooting device in the specification can be applied to computer equipment. The apparatus embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. In the case of software implementation, as a logical means, the device is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for operation through the processor of the computer device where the device is located. In terms of hardware, as shown in fig. 5, the present disclosure is a hardware structure diagram of a computer device in which a camera angle adjustment apparatus of a camera device is located, and except for the processor 510, the network interface 520, the memory 530, and the nonvolatile memory 540 shown in fig. 5, a computer device in which a camera angle adjustment apparatus 531 of a camera device is located in an embodiment may further include other hardware according to an actual function of the device, which is not described again.

As shown in fig. 6, the present specification is a block diagram of a camera angle adjusting apparatus of a camera apparatus according to an exemplary embodiment, the camera angle adjusting apparatus of the camera apparatus includes a support and a camera, the camera is movably connected to the support, the camera apparatus is used for capturing a face image, and the camera angle adjusting apparatus of the camera apparatus includes:

an information obtaining module 62, configured to: acquiring position information of a face in an image, wherein the image comprises an image acquired by a camera device at an existing initial shooting angle;

an angle correction module 64 for: calculating a correction shooting angle of the camera according to the position information of the face in the image;

an angle adjustment module 66 for: and controlling the supporting part to adjust the shooting angle of the camera to the corrected initial shooting angle according to the corrected shooting angle.

In one embodiment, a face recognition device connected to the camera device is used for performing face recognition on an image acquired by the camera device, and determining position information of a face in the image during the recognition process, wherein the position information of the face in the image is acquired and recorded from the face recognition device.

In one embodiment, the information acquisition module 62 is configured to: when the preset adjusting condition is met, acquiring the position information of the face in the image;

the face recognition failure times reach a preset failure time threshold;

the preset angle adjustment time is up;

and carrying out face recognition on the image acquired by the camera device.

In one embodiment, the apparatus further comprises an angle initialization module (not shown in fig. 6) for:

In one embodiment, the apparatus further comprises a test module (not shown in fig. 6) for:

acquiring an image acquired by a camera device in a preset camera test mode;

In one embodiment, the apparatus further comprises a real-time adjustment module (not shown in fig. 6) for:

acquiring an image currently acquired by a camera device;

In one embodiment, the acquiring, by the real-time adjustment module, an image currently acquired by a camera includes: and acquiring the image currently acquired by the camera device after the interval of the wakeup start of the camera device is appointed.

As shown in fig. 7, the present specification is a block diagram of a face recognition system according to an exemplary embodiment, which includes a face recognition terminal 72, a face recognition server 74 and an angle adjusting device 76;

the face recognition terminal 72 comprises a camera device for collecting a face image, the camera device comprises a support part and a camera, and the camera is movably connected to the support part;

the face recognition server 74 is configured to perform face recognition on a face image collected by the face recognition terminal;

the angle adjustment device 76 is configured to: acquiring position information of a face in an image, wherein the image comprises an image acquired by a camera device under an existing initial shooting angle; calculating a correction shooting angle of the camera according to the position information of the face in the image; and controlling the supporting part to adjust the shooting angle of the camera to the corrected initial shooting angle according to the corrected shooting angle.

For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, wherein the modules described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in the specification. One of ordinary skill in the art can understand and implement it without inventive effort.

Accordingly, embodiments of the present specification further provide a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method according to any of the above embodiments when executing the program.

All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

Accordingly, the present specification further provides a computer storage medium, in which program instructions are stored, and the program instructions implement the method according to any one of the above embodiments.

Embodiments of the present description may take the form of a computer program product embodied on one or more storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having program code embodied therein. Computer-usable storage media include permanent and non-permanent, removable and non-removable media, and may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of the storage medium of the computer include, but are not limited to: phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technologies, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic tape storage or other magnetic storage devices, or any other non-transmission medium, may be used to store information that may be accessed by a computing device.

Other embodiments of the present description will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This specification is intended to cover any variations, uses, or adaptations of the specification following the general principles of the specification and including such departures from the present disclosure as come within known or customary practice in the art to which the specification pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the specification being indicated by the following claims.

It will be understood that the present description is not limited to the precise arrangements described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the description is limited only by the appended claims.

The above description is only a preferred embodiment of the present disclosure, and should not be taken as limiting the present disclosure, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A camera angle adjusting method of a camera device comprises a supporting part and a camera, wherein the camera is movably connected to the supporting part and is used for collecting face images, and the method comprises the following steps:

controlling the supporting part to adjust the shooting angle of the camera to the initial shooting angle;

2. The method of claim 1, the image comprising at least: and correcting the initial shooting angle last time and then acquiring an image by the camera device during the current time.

3. The method according to claim 1, wherein a face recognition device connected to the camera device is used for performing face recognition on the image acquired by the camera device, and determining the position information of the face in the image during the recognition process, wherein the position information of the face in the image is acquired from the face recognition device and recorded.

4. The method of claim 3, wherein the obtaining of the position information of the human face in the image comprises: when the preset adjusting condition is met, acquiring the position information of the face in the image;

the face recognition failure times reach a preset failure time threshold;

the preset angle adjustment time is up;

and carrying out face recognition on the image acquired by the camera device.

5. The method of claim 1, further comprising:

acquiring an image acquired by a camera device in a preset camera test mode;

if the face exists in the image and the face is in the designated area in the image, outputting prompt information of successful test; or the like, or, alternatively,

if the image has a part of face, determining an adjusting direction according to the position of the face in the image, and controlling the supporting part to finely adjust the shooting angle of the camera according to a first preset angle step length along the adjusting direction; if the adjusted camera device collects images containing complete faces, the current shooting angle of the camera is used for updating the existing initial shooting angle; or the like, or, alternatively,

6. The method of any of claims 1 to 5, further comprising:

acquiring an image currently acquired by a camera device;

7. The method of claim 6, the acquiring an image currently acquired by a camera, comprising: and acquiring the image currently acquired by the camera device after the interval of the wakeup start of the camera device is appointed.

8. The method of claim 6, further comprising: and after the face recognition is finished, the control supporting part adjusts the shooting angle of the camera back to the initial shooting angle.

9. The utility model provides a camera angle adjusting device of camera device, camera device includes supporting part and camera, and camera swing joint is on the supporting part, camera device is used for gathering people's face image, camera device's camera angle adjusting device includes:

an information acquisition module to: when the camera device is started for the first time, the height of a camera in the camera device from the ground, the preset crowd height range, the average length of a human face and the distance between a person and the vertical plane where the camera is located are obtained, and the initial shooting angle of the camera is determined; controlling the supporting part to adjust the shooting angle of the camera to the initial shooting angle; acquiring position information of a face in an image, wherein the image comprises an image acquired by a camera device under an existing initial shooting angle;

10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 8 when executing the program.

11. A face recognition system comprises a face recognition terminal, a face recognition server and an angle adjusting device; the face recognition terminal comprises a camera device for collecting a face image, the camera device comprises a supporting part and a camera, and the camera is movably connected to the supporting part; the face recognition server is used for carrying out face recognition on a face image collected by the face recognition terminal;

the angle adjustment device is used for: