WO2019061542A1

WO2019061542A1 - Video capturing method and device, and computer readable storage medium

Info

Publication number: WO2019061542A1
Application number: PCT/CN2017/105162
Authority: WO
Inventors: 杨玉琳
Original assignee: 深圳传音通讯有限公司
Priority date: 2017-09-30
Filing date: 2017-09-30
Publication date: 2019-04-04
Also published as: CN111543047A

Abstract

Disclosed is a video capturing method, the video capturing method comprising the following steps: performing a face recognition on an image in a viewing frame area when video capturing is enabled; acquiring target image parameter values corresponding to a user facial image when the user facial image is recognized; and carrying out a corresponding image exposure processing on the image in the viewing frame area according to a logical comparison relationship between designated target image parameter values and preset image parameter values. Further disclosed are a video capturing device and a computer readable storage medium. The present invention realizes automatic image brightening during a process of capturing a video, thereby improving the person image brightness of the video, and optimizing video quality.

Description

Video shooting method, device and computer readable storage medium

Technical field

The present invention relates to the field of image imaging, and more particularly to a video capture method, apparatus, and computer readable storage medium.

Background technique

Nowadays, the imaging quality requirements for mobile phone photographing and recorded video are constantly increasing. At present, the mobile phone has been photographed to enhance the portrait, but the automatic portrait highlighting function is not available when recording the video, resulting in insufficient brightness of the portrait in the video, especially when the subject is darker, there will be obvious underexposure of the portrait; In the case of backlights and darker environments, there is also a situation in which the subject of the subject is dark.

The above content is only used to assist in understanding the technical solutions of the present invention, and does not constitute an admission that the above is prior art.

Summary of the invention

A main object of the present invention is to provide a video capture method, apparatus, and computer readable storage medium, which are directed to solving the problem of insufficient portrait exposure caused by the automatic portrait highlighting function when recording video.

To achieve the above object, the present invention provides a video capture method, the video capture method comprising the following steps:

Perform face recognition on the image of the framing area when starting video shooting;

Obtaining a target image parameter value corresponding to the user facial image when the user facial image is recognized;

Corresponding image exposure processing is performed on the image of the framing frame area according to a logical comparison relationship between the specified target image parameter value and the preset image parameter value.

Preferably, the target image parameter value corresponding to the user facial image includes: a portrait area image brightness FV in the user's face image, an area picture brightness BV other than the user's face image, and an image area of the portrait area in the view frame area. Area ratio R;

The preset image parameter value includes a portrait area target brightness FT in the user's face image, wherein the effective area of the portrait area target brightness FT is a ≤ FT ≤ b.

Preferably, the step of performing a corresponding image exposure process on the image of the framing frame area according to the logical comparison relationship between the specified target image parameter value and the preset image parameter value comprises:

Comparing the value of the FV with the value of the effective interval of the FT;

When FV < a, let FT = a;

According to the FT, the image of the framing frame area is subjected to exposure compensation such that the portrait area picture brightness FV is equal to the value a.

Preferably, the step of comparing the value of the FV with the value of the effective interval of the FT further includes:

When FV>b, let FT=b;

According to the FT, the image of the framing frame area is subjected to exposure compensation such that the portrait area picture brightness FV is equal to the value b.

When a ≤ FV ≤ b, let FT = R * FV + (1-R) * BV;

According to the FT, the image of the framing area is subjected to exposure compensation such that the portrait area picture brightness FV is equal to the FT.

Preferably, when the user facial image is recognized, the step of acquiring the target image parameter value corresponding to the user facial image comprises:

Numbering each portrait corresponding to the recognized user's face image;

The target image parameter value of the portrait corresponding to the selected number in the image is acquired according to the number selected by the user.

In addition, in order to achieve the above object, the present invention further provides a video photographing apparatus, comprising: a camera, a memory, a processor, and being stored on the memory and operable on the processor Video capture device, where:

The camera is used for video shooting;

The steps of the video capture method as described above are implemented when the video capture device is executed by the processor.

In addition, in order to achieve the above object, the present invention further provides a computer readable storage medium, wherein the computer readable storage medium stores a video capture program, and the video capture program is executed by a processor as described above. The steps of the video capture method described.

A video shooting method, device and computer readable storage medium provided by embodiments of the present invention,

By performing face recognition on the image of the framing frame area when starting the video shooting, when the image of the user is recognized, the corresponding image parameter value is acquired; after the image parameter value is compared with the target image parameter value, the framing area is The target area image performs corresponding image brightening processing, thereby realizing automatic brightening of the image during the shooting of the video, improving the portrait brightness of the video, and optimizing the video quality.

DRAWINGS

1 is a schematic structural diagram of a video capture apparatus according to an embodiment of the present invention;

2 is a schematic flow chart of a first embodiment of a video capturing method according to the present invention;

3 is a schematic flow chart of a second embodiment of a video capturing method according to the present invention;

4 is a schematic flow chart of a third embodiment of a video capturing method according to the present invention;

FIG. 5 is a schematic diagram of an example of a second embodiment of a video capture method according to the present invention.

The implementation, functional features, and advantages of the present invention will be further described in conjunction with the embodiments.

Detailed ways

It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The main solution of the embodiment of the present invention is: performing facial recognition on the image of the framing frame area at the beginning of the video shooting; and acquiring the target image parameter value corresponding to the user facial image when the user facial image is recognized; And a logical comparison relationship between the target image parameter value and the preset image parameter value, and performing corresponding image exposure processing on the image of the framing frame area.

Since the existing portrait video cannot be automatically brightened, the portrait exposure is easily insufficient, and the present invention provides a solution that enables automatic portrait highlighting during video shooting when the subject's skin color is deep.

As shown in FIG. 1, FIG. 1 is a schematic structural diagram of a terminal of a video capturing apparatus according to an embodiment of the present invention.

The video capturing device of the embodiment of the present invention may be a mobile terminal device having a video capturing and displaying function, such as a smart phone, a digital camera, a video recorder, a tablet computer, a portable computer, or the like.

As shown in FIG. 1, the video capture device can include a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to implement connection communication between these components. The user interface 1003 can include a display, an input unit such as a keyboard, and the optional user interface 1003 can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface). The memory 1005 may be a high speed RAM memory or a stable memory (non-volatile) Memory), such as disk storage. The memory 1005 can also optionally be a storage device independent of the aforementioned processor 1001.

The video capture device can include a camera, RF (Radio) Frequency, RF) circuits, sensors, audio circuits, WiFi modules, and more. Among them, sensors such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. Of course, the video capturing device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, and the like, and details are not described herein.

It will be understood by those skilled in the art that the terminal structure shown in FIG. 1 does not constitute a limitation to the terminal, and may include more or less components than those illustrated, or a combination of certain components, or different component arrangements.

As shown in FIG. 1, an operating system, a network communication module, a user interface module, and a video capture program may be included in the memory 1005 as a computer storage medium.

In the terminal shown in FIG. 1, the network interface 1004 is mainly used to connect to the background server and perform data communication with the background server; the user interface 1003 is mainly used to connect the client (user end), and perform data communication with the client; and the processor 1001 can be used to call a video capture program stored in the memory 1005 and perform the following operations:

The image target parameter value may include a portrait area image brightness FV in the user's face image, an area picture brightness BV other than the user's face image, and an area ratio R of the image area in the image frame area of the view frame area;

Further, the processor 1001 can call the video capture program stored in the memory 1005, and also performs the following operations:

When FV < a, let FT = a;

According to the FT, exposure compensation is performed on the target area image of the framing frame area such that the portrait area screen brightness FV is equal to the value a.

When FV>b, let FT=b;

According to the FT, exposure compensation is performed on the target area image of the framing frame area such that the portrait area picture brightness FV is equal to the value b.

When a ≤ FV ≤ b, let FT = R * FV + (1-R) * BV;

And performing exposure compensation on the target area image of the framing frame area according to the FT, so that the portrait area screen brightness FV is equal to the FT.

Numbering each portrait corresponding to the recognized user's face image;

Referring to FIG. 2, a first embodiment of the present invention provides a video capture method, where the video capture method includes:

Step S10, performing facial recognition on the image of the framing frame area when the video shooting is started;

Step S20, when the user facial image is recognized, acquiring a target image parameter value corresponding to the user facial image;

In a specific implementation, when a video camera having a video camera function such as a smart phone or a digital camera is used for video shooting, face recognition is performed on the image of the framing frame area; and the function of face recognition is also selected at a certain time of shooting the video. The facial recognition method may include, but is not limited to, a feature face recognition method, a reference template method, and a portrait rule method; in the embodiment of the present invention, an ISP is preferably used. (Image Signal Processing) technology by FD (Fourier Descriptors, Fourier descriptors) detect the position of the face and face in the image in the image. The Fourier descriptor method is a conventional means in the art and will not be described here.

After the image of the user's face is recognized, the target image parameter value corresponding to the facial image is further obtained, which may specifically include: a portrait area image brightness FV in the user's face image, an area picture brightness BV other than the user's face image, and the portrait area is The area of the image area of the view frame area occupies a ratio R.

Step S30, performing corresponding image exposure processing on the image of the framing frame area according to a logical comparison relationship between the specified target image parameter value and the preset image parameter value.

Specifically, the target image parameter value for performing the logical comparison is the portrait area screen brightness FV, and the preset image parameter value includes the portrait area target brightness FT in the user face image, wherein the effective range of the portrait area target brightness FT is a ≤ FT ≤ b. By comparing the effective interval values of FV and FT, the corresponding image enhancement process for the target area image of the framing frame area can be obtained, thereby realizing automatic portrait brightening. For example, when FV<a, let FT=a, according to the FT, perform exposure compensation on the target area image of the framing frame area, so that the portrait area picture brightness FV is equal to the value a; in other words, when the portrait area When the actual brightness is lower than the target brightness, the portrait brightness is dark, and the exposure compensation for the portrait can be performed to brighten the portrait brightness. It should be noted that the framing area image may further include one or more portrait areas for performing image brightening processing when there are multiple portraits, and may also include area image images other than the user's facial image, for example, when the video shooting environment is used. When it is dark, similar exposure compensation processing is performed on the environment screen.

In this embodiment, by performing facial recognition on the image of the framing frame area when starting the video shooting, when the user facial image is recognized, the corresponding target parameter value is acquired; and according to the specified target image parameter value and the preset The logical comparison relationship of the image parameter values performs corresponding image exposure processing on the image of the framing frame area, thereby solving the problem of insufficient brightness of the captured image (especially the dark-skinned portrait), improving the video quality, and prompting the user experience.

Further, referring to FIG. 3, a second embodiment of the present invention provides a video capturing method. According to the embodiment shown in FIG. 2, the logical comparison relationship between a specified target image parameter value and a preset image parameter value is performed. The step of performing corresponding image exposure processing on the image of the framing frame area includes:

Step S31, comparing the value of the FV with the value of the effective interval of the FT;

Step S32, when FV < a, let FT = a;

Step S33, performing exposure compensation on the image of the framing frame area according to the FT, so that the portrait area picture brightness FV is equal to the value a.

Step S34, when FV>b, let FT=b;

Step S35, performing exposure compensation on the image of the framing frame area according to the FT, so that the portrait area screen brightness FV is equal to the value b.

Step S36, when a ≤ FV ≤ b, let FT = R * FV + (1-R) * BV;

Step S37, performing exposure compensation on the image of the framing frame area according to the FT, so that the portrait area screen brightness FV is equal to the FT.

For example, as shown in FIG. 5( a ), the portrait of the currently captured video is darker, that is, FV<a. At this time, the FT is taken as the lower limit value a of the original effective interval, and the framing is performed according to the FT. The image of the frame area is subjected to exposure compensation such that the portrait area picture brightness FV is equal to the value a. Thus, as shown in FIG. 5(b), the portrait can be correspondingly brightened, and the contrast and display effect of the portrait image is enhanced. When the portrait is too bright due to skin color, lighting, etc., the brightness of the portrait can be appropriately reduced by exposure compensation to coordinate the portrait with the environmental background.

In this embodiment, by comparing the value of the FV with the value of the effective interval of the FT, the image of the framing frame area is subjected to exposure compensation processing, thereby increasing or decreasing the brightness of the portrait, so that the portrait in the video picture is more clear and clear, and the environment background is more clear. coordination.

Referring to FIG. 4, a third embodiment of the present invention provides a video capturing method. According to the embodiment shown in FIG. 3, when the user facial image is recognized, the target image parameter value corresponding to the user facial image is acquired. The steps include:

Step S21, numbering each portrait corresponding to the recognized facial image of the user;

Step S22: Acquire a target image parameter value of the portrait corresponding to the selected number in the image according to the number selected by the user.

When shooting a video, there may be multiple portraits in the frame of the viewfinder area. If some people have darker skin and some people have a normal skin tone, the user wants to brighten the image based on the darker face. At this time, each portrait corresponding to the recognized user's facial image may be numbered according to the face recognition technology, and the user may select one or more portraits and further acquire the target image parameter values of the corresponding portrait. It should be noted that when a plurality of portraits are selected, the target image parameter value finally used for the image exposure processing may be a weighted average of the target image parameter values of the respective selected portraits.

In an embodiment, by selecting the identified portraits in a targeted manner and acquiring the target image parameter values of the selected portraits, it is advantageous to refine the dependent parameter values in the image compensation processing in order to more accurately optimize the video images.

In addition, an embodiment of the present invention further provides a computer readable storage medium, where the video photographic storage program stores a video capture program, and when the video capture program is executed by the processor, the following operations are implemented:

The target image parameter value corresponding to the user facial image includes: a portrait area image brightness FV in the user's face image, an area picture brightness BV other than the user's face image, and an image area of the portrait area in the view frame area. Area ratio R;

Further, when the video capturing program is executed by the processor, the following operations are also implemented:

When FV < a, let FT = a;

When FV>b, let FT=b;

When a ≤ FV ≤ b, let FT = R * FV + (1-R) * BV;

Numbering each portrait corresponding to the recognized user's face image;

It is to be understood that the term "comprises", "comprising", or any other variants thereof, is intended to encompass a non-exclusive inclusion, such that a process, method, article, or It also includes other elements that are not explicitly listed, or elements that are inherent to such a process, method, item, or system. An element defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in a process, method, article, or system that includes the element, without further limitation.

The serial numbers of the embodiments of the present invention are merely for the description, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better. Implementation. Based on such understanding, portions of the technical solution of the present invention that contribute substantially or to the prior art may be embodied in the form of a software product stored in a storage medium (such as a ROM/RAM as described above). , a disk, an optical disk, including a number of instructions for causing a terminal device to perform the method described in various embodiments of the present invention.

The above are only the preferred embodiments of the present invention, and are not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformations made by the description of the present invention and the drawings are directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of the present invention.

Claims

A video capture method, characterized in that the video capture method comprises the following steps:

Perform face recognition on the image of the framing area when starting video shooting;

Obtaining a target image parameter value corresponding to the user facial image when the user facial image is recognized;

Corresponding image exposure processing is performed on the image of the framing frame area according to a logical comparison relationship between the specified target image parameter value and the preset image parameter value.
The video capture method according to claim 1, wherein the target image parameter value corresponding to the user's face image comprises: a portrait area image brightness FV in the user's face image, and an area picture brightness BV other than the user's face image, The area ratio R of the image area of the portrait area in the view frame area;

The preset image parameter value includes a portrait area target brightness FT in the user's face image, wherein the effective area of the portrait area target brightness FT is a ≤ FT ≤ b.
The video capture method according to any one of claims 1 to 2, wherein the performing a corresponding comparison on the image of the framing frame area according to a logical comparison relationship between the specified target image parameter value and the preset image parameter value The steps of image exposure processing include:

Comparing the value of the FV with the value of the effective interval of the FT;

When FV < a, let FT = a;

According to the FT, the image of the framing frame area is subjected to exposure compensation such that the portrait area picture brightness FV is equal to the value a.
The video capture method of claim 3, wherein the step of comparing the value of the FV with the value of the effective interval of the FT further comprises:

When FV>b, let FT=b;

According to the FT, exposure compensation is performed on the target area image of the framing frame area such that the portrait area picture brightness FV is equal to the value b.
The video capture method according to claim 3, wherein the step of comparing the value of the FV with the value of the effective interval of the FT further comprises:

When a ≤ FV ≤ b, let FT = R * FV + (1-R) * BV;

And performing exposure compensation on the target area image of the framing frame area according to the FT, so that the portrait area screen brightness FV is equal to the FT.
The video capturing method according to claim 1, wherein the step of acquiring a target image parameter value corresponding to the user facial image when the user facial image is recognized comprises:

Numbering each portrait corresponding to the recognized user's face image;

The target image parameter value of the portrait corresponding to the selected number in the image is acquired according to the number selected by the user.
A video photographing apparatus, comprising: a camera, a memory, a processor, and a video photographing apparatus stored on the memory and operable on the processor, wherein:

The camera is used for video shooting;

The step of implementing the video capture method according to any one of claims 1 to 6 when the video capture device is executed by the processor.
A computer readable storage medium, wherein the computer readable storage medium stores a video capture program, the video capture program being executed by a processor to implement the method of any one of claims 1 to 6. The steps of the video capture method.