CN110263695A

CN110263695A - Location acquiring method, device, electronic equipment and the storage medium at face position

Info

Publication number: CN110263695A
Application number: CN201910517973.5A
Authority: CN
Inventors: 曹占魁
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2019-06-14
Filing date: 2019-06-14
Publication date: 2019-09-20
Anticipated expiration: 2039-06-14
Also published as: CN110263695B

Abstract

Location acquiring method, device, electronic equipment and storage medium of the disclosure about a kind of face position, are related to field of computer technology.The described method includes: obtaining the ratio that face is located at face area and face except the first screen-picture；When ratio meets goal condition, obtain the second screen-picture in target site first position and the second screen-picture in include target site first object region；The change in location information of image characteristic point in first object region and the second target area is obtained, the second target area is first object region corresponding region including target site in the second screen-picture；Based on first position and change in location information, the second position of target site in the first screen-picture is obtained.The case where position at the disclosure still available accurate face position when screen-picture only includes part face, accuracy is good, and there is no identifications, recognition effect is good.

Description

Location acquiring method, device, electronic equipment and the storage medium at face position

Technical field

This disclosure relates to field of computer technology more particularly to a kind of location acquiring method, device, the electronics at face position Equipment and storage medium.

Background technique

With the development of computer technology, face recognition technology is using more and more extensive, for example, face recognition technology can be with It is combined with augmented reality (Augmented Reality, AR) technology, recognition of face is carried out to screen-picture, on face position Add other dummy objects.

In the related technology, the location acquiring method at face position is usually to acquire screen-picture, directly to collected screen Curtain picture carries out recognition of face, obtains the position at face position.

In the above method sometimes face only have part be located at screen-picture in, in this case directly to screen-picture into Row recognition of face, may because of the face position that the position in screen-picture does not cause entirely position may inaccuracy, It is also possible to the case where will appear recognition failures, recognition effect is poor.

Summary of the invention

The disclosure provides location acquiring method, device, electronic equipment and the storage medium at a kind of face position, at least to solve Certainly in the related technology recognition result inaccuracy, recognition failures and recognition effect difference problem.The technical solution of the disclosure is as follows:

According to the first aspect of the embodiments of the present disclosure, a kind of location acquiring method at face position is provided, comprising:

Obtain the ratio that face is located at face area and the face except the first screen-picture；

When the ratio meets goal condition, the first position of target site and described is obtained in the second screen-picture It include the first object region of the target site in second screen-picture, first screen-picture and second screen are drawn Face is the screen-picture collected different moments；

Obtain the change in location information of image characteristic point in the first object region and the second target area, described second Target area is the first object region corresponding region including the target site in second screen-picture；

Based on the first position and the change in location information, target site described in first screen-picture is obtained The second position.

In a kind of possible implementation, it is described obtain face be located at face area except the first screen-picture with it is described The ratio of face, including any one of following:

Face critical point detection is carried out to first screen-picture, the face is obtained and is located at first screen-picture In key point quantity, obtain the difference of destination number and the quantity and the ratio of the destination number；

Face critical point detection is carried out to first screen-picture, the face is obtained and is located at first screen-picture In key point position and the face edge key point position, first screen-picture is located at according to the face In key point position and the face edge key point position, obtain the face and be located at first screen-picture Key point the first area and second area of the first area that are surrounded, obtain the second area and first area The ratio of difference and the second area, the area for the second area that the second area is surrounded by the edge key point.

It is described to obtain characteristics of image in the first object region and the second target area in a kind of possible implementation The change in location information of point, including any one of following:

Feature extraction is carried out to the first object region and second target area respectively, obtains the first object In region in the position of the first image characteristic point and second target area the second image characteristic point position, based on described the The position of the position of one image characteristic point and second image characteristic point obtains the change in location information；

First screen-picture and second screen-picture are matched, obtained in first screen-picture The similarity of second target area in one target area and second screen-picture is based on the similarity, obtains described the The change in location information of image characteristic point in one target area and second target area.

It is described that the first object region and second target area are carried out respectively in a kind of possible implementation Feature extraction obtains in the first object region the second figure in the position of the first image characteristic point and second target area As the position of characteristic point, comprising:

Feature extraction is carried out to the first object region and second target area respectively, obtains the first object In region in the position of multiple first image characteristic points and second target area multiple second image characteristic points position；

The position of the position based on the first image characteristic point and second image characteristic point obtains institute's rheme Set change information, comprising:

According to more in the position and second target area of the first image characteristic points multiple in the first object region The position of a second image characteristic point obtains between the multiple first image characteristic point and the multiple second image characteristic point Mean place change information, using the mean place change information as in the first object region and the second target area The change in location information of image characteristic point.

It is described when the ratio meets goal condition in a kind of possible implementation, it obtains in the second screen-picture It include the first object region of the target site in the first position of target site and second screen-picture, including under Any one of state:

When obtaining mode is first mode and the ratio is greater than the first proportion threshold value, the second screen of the acquisition is executed It include the first object region of the target site in the first position of target site and second screen-picture in picture The step of, the first mode is the mode that the second position is obtained based on recognition of face mode；

When obtaining mode is second mode and the ratio is greater than the second proportion threshold value, executes and obtain the second screen-picture The step in the first object region in the first position of middle target site and second screen-picture including the target site Suddenly, second proportion threshold value is less than first proportion threshold value, and the second mode is that the position based on image characteristic point becomes Change the mode of the acquisition of information second position.

It is described when the ratio meets goal condition in a kind of possible implementation, it obtains in the second screen-picture Include the first object region of the target site in the first position of target site and second screen-picture, also wraps It includes:

When obtaining mode is that first mode and the ratio are greater than the first proportion threshold value, by the obtaining mode from described First mode switches to the second mode.

In a kind of possible implementation, it is described obtain face be located at face area except the first screen-picture with it is described After the ratio of face, the method also includes any one of following:

When obtaining mode is first mode and the ratio is less than or equal to the first proportion threshold value, to first screen Picture carries out recognition of face, obtains the second position of target site described in first screen-picture, the first mode is The mode of the second position is obtained based on recognition of face mode；

When obtaining mode is second mode and the ratio is less than or equal to the second proportion threshold value, to first screen Picture carries out recognition of face, obtains the second position of target site described in first screen-picture, the second ratio threshold Value is less than first proportion threshold value, and the second mode is the change in location acquisition of information second position based on image characteristic point Mode.

In a kind of possible implementation, it is described obtain face be located at face area except the first screen-picture with it is described After the ratio of face, the method also includes:

When obtaining mode is second mode and the ratio is less than or equal to the second proportion threshold value, mode will acquire from institute It states second mode and switches to the first mode.

In a kind of possible implementation, the method also includes:

When obtaining mode is first mode and the ratio is greater than the first proportion threshold value, or, when obtaining mode is second When mode and the ratio are less than or equal to the second proportion threshold value, recognition of face is carried out to first screen-picture, obtains institute State the third place of target site described in the first screen-picture；

It executes and obtains the first position of target site in the second screen-picture, first object region and change in location information Step is based on the first position and the change in location information, obtains target site described in first screen-picture 4th position；

Based on the third place and the 4th position, the of target site described in first screen-picture is obtained Two positions.

It is described when the ratio meets goal condition in a kind of possible implementation, it obtains in the second screen-picture It include the first object region of the target site in the first position of target site and second screen-picture, comprising:

When the ratio is greater than the first proportion threshold value, first of target site in the second screen-picture of the acquisition is executed Include the steps that the first object region of the target site in position and second screen-picture；

The acquisition face is located at after the ratio of the face area except the first screen-picture and the face, the side Method further include:

When the ratio is less than or equal to the second proportion threshold value, recognition of face is carried out to first screen-picture, is obtained To the second position of target site described in first screen-picture.

In a kind of possible implementation, first proportion threshold value is identical as second proportion threshold value；

It is described when the ratio be less than or equal to the second proportion threshold value when, to first screen-picture carry out face knowledge Not, the second position of target site described in first screen-picture is obtained, comprising:

When the ratio is less than or equal to first proportion threshold value, execute described to first screen-picture progress Recognition of face, the step of obtaining the second position of target site described in first screen-picture.

In a kind of possible implementation, first proportion threshold value is greater than second proportion threshold value；

The method also includes:

When the ratio is less than first proportion threshold value, and the ratio is greater than second proportion threshold value, execute Described the step of recognition of face is carried out to first screen-picture, obtain target site described in first screen-picture The third place；

It is described to be based on the third place and the 4th position in a kind of possible implementation, obtain described first The second position of target site described in screen-picture, comprising:

Summation is weighted to the third place and the 4th position, obtains mesh described in first screen-picture Mark the second position at position.

In a kind of possible implementation, the weight of the third place and the 4th position is based on the ratio and the The relationship of one proportion threshold value determines；Or, the third place and the weight of the 4th position are based on the ratio and the second ratio The relationship of example threshold value determines；It is cut or, the third place and the weight of the 4th position are based on present system time with mode The relationship for changing duration determines.

It is described to be based on the first position and the change in location information in a kind of possible implementation, described in acquisition The second position of target site described in first screen-picture, comprising:

Obtain the first position and the second position change information and value, it regard described and value as first screen The second position of target site described in curtain picture.

In a kind of possible implementation, the first position of target site and described of obtaining in the second screen-picture Before first object region in second screen-picture including the target site, the method also includes any one of following:

The former frame screen-picture of first screen-picture is obtained as second screen-picture；

The first frame screen-picture in collected multiframe screen-picture is obtained as second screen-picture；

Obtain last frame screen-picture of the ratio described in collected multiframe screen-picture less than the first proportion threshold value As second screen-picture.

According to the second aspect of an embodiment of the present disclosure, a kind of position acquisition device at face position is provided, comprising:

Ratio acquisition unit, be configured as executing obtain face be located at face area except the first screen-picture with it is described The ratio of face；

Position acquisition unit is configured as executing when the ratio meets goal condition, obtain in the second screen-picture It include the first object region of the target site in the first position of target site and second screen-picture, described the One screen-picture and second screen-picture are the screen-picture collected different moments；

Information acquisition unit is configured as executing characteristics of image in the acquisition first object region and the second target area The change in location information of point, second target area are that the first object region is corresponding in second screen-picture Region including the target site；

The position acquisition unit is additionally configured to execute based on the first position and the change in location information, obtain Take the second position of target site described in first screen-picture.

In a kind of possible implementation, the ratio acquisition unit is configured as executing any one of following:

In a kind of possible implementation, the information acquisition unit is configured as executing any one of following:

In a kind of possible implementation, the information acquisition unit is configured as executing respectively to the first object area Domain and second target area carry out feature extraction, obtain the position of multiple first image characteristic points in the first object region Set the position with the second image characteristic points multiple in second target area；

The information acquisition unit is configured as executing according to the first image characteristic points multiple in the first object region Position and second target area in multiple second image characteristic points position, obtain the multiple first image characteristic point Mean place change information between the multiple second image characteristic point, using the mean place change information as described in The change in location information of image characteristic point in first object region and the second target area.

In a kind of possible implementation, the position acquisition unit is configured as executing any one of following:

In a kind of possible implementation, the position acquisition unit is additionally configured to execute when obtaining mode is the first mould When formula and the ratio are greater than the first proportion threshold value, the obtaining mode is switched into second mould from the first mode Formula.

In a kind of possible implementation, the position acquisition unit is additionally configured to execute any one of following:

In a kind of possible implementation, described device further include:

First mode switch unit is configured as executing when obtaining mode is second mode and the ratio is less than or equal to When the second proportion threshold value, it will acquire mode from the second mode and switch to the first mode.

In a kind of possible implementation, the position acquisition unit is additionally configured to execute:

In a kind of possible implementation, the position acquisition unit is configured as executing when the ratio is greater than the first ratio When example threshold value, executes described obtain in the second screen-picture and wrapped in the first position of target site and second screen-picture The step of including the first object region of the target site；

The position acquisition unit is additionally configured to execute when the ratio is less than or equal to the second proportion threshold value, to institute It states the first screen-picture and carries out recognition of face, obtain the second position of target site described in first screen-picture.

The position acquisition unit is configured as executing when the ratio is less than or equal to first proportion threshold value, holds Row is described to carry out recognition of face to first screen-picture, obtains second of target site described in first screen-picture The step of position.

The position acquisition unit is configured as executing:

In a kind of possible implementation, the position acquisition unit is configured as executing to the third place and described 4th position is weighted summation, obtains the second position of target site described in first screen-picture.

In a kind of possible implementation, the position acquisition unit, which is configured as executing, obtains the first position and institute State second position change information and value, by second described and that value is as target site described in first screen-picture It sets.

In a kind of possible implementation, described device further includes picture acquiring unit, and the picture acquiring unit is matched It is set to and executes following any one:

According to the third aspect of an embodiment of the present disclosure, a kind of electronic equipment is provided, the electronic equipment includes:

One or more processors；

For storing one or more memories of one or more of processor-executable instructions；

Wherein, one or more of processors are configured as executing the side of being able to achieve of first aspect and first aspect Operation performed by the location acquiring method at face position described in any one of formula.

According to a fourth aspect of embodiments of the present disclosure, a kind of storage medium is provided, the instruction in the storage medium is by electronics When the processor of equipment executes, so that the electronic equipment is able to carry out the possibility implementation of first aspect and first aspect Any one of described in face position location acquiring method performed by operation.

According to a fifth aspect of the embodiments of the present disclosure, a kind of computer program product, including one or more instruction are provided, When one or more instruction can be executed by the processor of control equipment, so that the control equipment is able to carry out first aspect And operation performed by the location acquiring method at face position described in any one of possibility implementation of first aspect.

The technical scheme provided by this disclosed embodiment at least bring it is following the utility model has the advantages that

The embodiment of the present disclosure is met by the ratio of the face area and entire face that are located at except screen-picture in face When certain condition, the change of face in the position and two screen-pictures by obtaining target site in other screen-picture Change situation is not directly to be realized by recognition of face mode, is shielding to obtain the position of the target site in active screen The position at curtain picture still available accurate face position when only including part face, accuracy is good, and there is no identifications Situation, recognition effect are good.

It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not The disclosure can be limited.

Detailed description of the invention

The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure Example, and together with specification for explaining the principles of this disclosure, do not constitute the improper restriction to the disclosure.

Fig. 1 is a kind of flow chart of the location acquiring method at face position shown according to an exemplary embodiment.

Fig. 2 is a kind of flow chart of the location acquiring method at face position shown according to an exemplary embodiment.

Fig. 3 is a kind of position acquisition device block diagram at face position shown according to an exemplary embodiment.

Fig. 4 is a kind of structural block diagram of terminal shown according to an exemplary embodiment.

Fig. 5 is a kind of structural schematic diagram of server shown according to an exemplary embodiment.

Specific embodiment

In order to make ordinary people in the field more fully understand the technical solution of the disclosure, below in conjunction with attached drawing, to this public affairs The technical solution opened in embodiment is clearly and completely described.

It should be noted that the specification and claims of the disclosure and term " first " in above-mentioned attached drawing, " Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way Data be interchangeable under appropriate circumstances, so as to embodiment of the disclosure described herein can in addition to illustrating herein or Sequence other than those of description is implemented.Embodiment described in following exemplary embodiment does not represent and disclosure phase Consistent all embodiments.On the contrary, they are only and as detailed in the attached claim, the disclosure some aspects The example of consistent device and method.

Fig. 1 is a kind of flow chart of the location acquiring method at face position shown according to an exemplary embodiment, such as Fig. 1 Shown, this method can be applied in electronic equipment, comprising the following steps:

In step s 11, the ratio that face is located at face area and the face except the first screen-picture is obtained.

In step s 12, when the ratio meets goal condition, first of target site in the second screen-picture is obtained Set and second screen-picture in include the target site first object region, first screen-picture and second screen Picture is the screen-picture collected different moments.

In step s 13, the change in location letter of image characteristic point in the first object region and the second target area is obtained Breath, second target area are the first object region corresponding area including the target site in second screen-picture Domain.

In step S14, based on the first position and the change in location information, the target in first screen-picture is obtained The second position at position.

In a kind of possible implementation, which is located at face area and the face except the first screen-picture Ratio, including it is any one of following:

Face critical point detection is carried out to first screen-picture, obtains the pass that the face is located in first screen-picture The quantity of key point obtains the difference of destination number and the quantity and the ratio of the destination number；

Face critical point detection is carried out to first screen-picture, obtains the pass that the face is located in first screen-picture The position of the edge key point of the position and face of key point is located at the key point in first screen-picture according to the face The position of the edge key point of position and the face, obtain that the face is located at that the key point of first screen-picture surrounded the First area and second area in one region obtain the difference of the second area and first area and the ratio of the second area Value, the area for the second area which is surrounded for the edge key point.

In a kind of possible implementation, image characteristic point in the acquisition first object region and the second target area Change in location information, including any one of following:

Feature extraction is carried out to the first object region and second target area respectively, is obtained in the first object region The position of second image characteristic point in the position of first image characteristic point and second target area, is based on first characteristics of image The position of point and the position of second image characteristic point, obtain the change in location information；

First screen-picture and second screen-picture are matched, first object in first screen-picture is obtained The similarity of second target area in region and second screen-picture, is based on the similarity, obtain the first object region and The change in location information of image characteristic point in second target area.

In a kind of possible implementation, this carries out feature to the first object region and second target area respectively and mentions It takes, obtains the position of the first image characteristic point and the second image characteristic point in second target area in the first object region Position, comprising:

Feature extraction is carried out to the first object region and second target area respectively, is obtained in the first object region The position of multiple second image characteristic points in the position of multiple first image characteristic points and second target area；

The position of the position based on first image characteristic point and second image characteristic point obtains change in location letter Breath, comprising:

According in the position of the first image characteristic points multiple in the first object region and second target area multiple the The position of two image characteristic points obtains the average bit between multiple first image characteristic point and multiple second image characteristic point Change information is set, using the mean place change information as image characteristic point in the first object region and the second target area Change in location information.

In a kind of possible implementation, when deserving the ratio and meeting goal condition, target in the second screen-picture is obtained It include the first object region of the target site in the first position at position and second screen-picture, including following any :

When obtaining mode is first mode and the ratio is greater than the first proportion threshold value, second screen-picture of acquisition is executed Include the steps that the first object region of the target site in the first position of middle target site and second screen-picture, it should First mode is the mode that the second position is obtained based on recognition of face mode；

When obtaining mode is second mode and the ratio is greater than the second proportion threshold value, executes and obtain in the second screen-picture Include the steps that the first object region of the target site in the first position of target site and second screen-picture, this Two proportion threshold values are less than first proportion threshold value, which is the change in location acquisition of information second based on image characteristic point The mode of position.

In a kind of possible implementation, when deserving the ratio and meeting goal condition, target in the second screen-picture is obtained It include the first object region of the target site in the first position at position and second screen-picture, further includes:

When obtaining mode is that first mode and the ratio are greater than the first proportion threshold value, by the obtaining mode from first mould Formula switches to the second mode.

In a kind of possible implementation, which is located at face area and the face except the first screen-picture Ratio after, this method further includes any one of following:

When obtaining mode is first mode and the ratio is less than or equal to the first proportion threshold value, to first screen-picture Recognition of face is carried out, the second position of the target site in first screen-picture is obtained, which is to be known based on face Other mode obtains the mode of the second position；

When obtaining mode is second mode and the ratio is less than or equal to the second proportion threshold value, to first screen-picture Carry out recognition of face, obtain the second position of the target site in first screen-picture, second proportion threshold value be less than this One proportion threshold value, the second mode are the mode of the change in location acquisition of information second position based on image characteristic point.

In a kind of possible implementation, which is located at face area and the face except the first screen-picture Ratio after, this method further include:

When obtaining mode is that second mode and the ratio are less than or equal to the second proportion threshold value, will acquire mode from this Two modes switch to the first mode.

In a kind of possible implementation, this method further include:

When obtaining mode is first mode and the ratio is greater than the first proportion threshold value, or, when obtaining mode is the second mould When formula and the ratio are less than or equal to the second proportion threshold value, recognition of face is carried out to first screen-picture, obtains first screen The third place of the target site in curtain picture；

It executes and obtains the first position of target site in the second screen-picture, first object region and change in location information Step obtains the 4th position of the target site in first screen-picture based on the first position and the change in location information；

Based on the third place and the 4th position, the second position of the target site in first screen-picture is obtained.

In a kind of possible implementation, when deserving the ratio and meeting goal condition, target in the second screen-picture is obtained It include the first object region of the target site in the first position at position and second screen-picture, comprising:

When the ratio is greater than the first proportion threshold value, the first position of target site in second screen-picture of acquisition is executed And include the steps that the first object region of the target site in second screen-picture；

The acquisition face is located at after the ratio of the face area except the first screen-picture and the face, and this method is also wrapped It includes:

When the ratio is less than or equal to the second proportion threshold value, recognition of face is carried out to first screen-picture, is somebody's turn to do The second position of the target site in first screen-picture.

When deserving the ratio less than or equal to the second proportion threshold value, recognition of face is carried out to first screen-picture, is obtained The second position of the target site in first screen-picture, comprising:

When the ratio is less than or equal to first proportion threshold value, executes this and face knowledge is carried out to first screen-picture Not, the step of obtaining the second position of the target site in first screen-picture.

In a kind of possible implementation, which is greater than second proportion threshold value；

This method further include:

When the ratio is less than first proportion threshold value, and the ratio is greater than second proportion threshold value, execute this to this One screen-picture carries out the step of recognition of face, obtains the third place of the target site in first screen-picture；

In a kind of possible implementation, first screen-picture should be obtained based on the third place and the 4th position In the target site the second position, comprising:

Summation is weighted to the third place and the 4th position, obtains the target site in first screen-picture The second position.

In a kind of possible implementation, the weight of the third place and the 4th position is based on the ratio and the first ratio The relationship of threshold value determines；Or, the relationship of the third place and the weight of the 4th position based on the ratio Yu the second proportion threshold value It determines；Or, the third place and the weight of the 4th position are determined based on the relationship of present system time and pattern switching duration.

In a kind of possible implementation, first screen should be obtained based on the first position and the change in location information The second position of the target site in picture, comprising:

Obtain the first position and the second position change information and value, this and value are used as in first screen-picture The second position of the target site.

In a kind of possible implementation, in second screen-picture of acquisition the first position of target site and this second Before first object region in screen-picture including the target site, this method further includes any one of following:

The ratio in collected multiframe screen-picture is obtained to make less than the last frame screen-picture of the first proportion threshold value For second screen-picture.

Fig. 2 is a kind of flow chart of the location acquiring method at face position shown according to an exemplary embodiment, such as Fig. 2 Shown, the location acquiring method at face position is applied in electronic equipment, includes the following steps.

In the step s 21, electronic equipment acquires the first screen-picture.

In the embodiments of the present disclosure, electronic equipment can have image collecting function, pass through the image collecting function, acquisition Image, and acquired image is shown in screen, the image shown in the screen is screen-picture.The electronic equipment can be with Screen-picture is acquired, screen-picture is handled, to determine the position at face position in the screen-picture.Specifically, electronics Equipment is sometime collecting the first screen-picture, and then by following step, to analyze first screen-picture, First screen-picture is identified in such a way that determination is using which kind of, to determine the position at face position.

In a kind of possible implementation, electronic equipment can acquire screen-picture in real time, carry out in real time to screen-picture Analysis obtains the position for wanting the face position of determination.It wherein, may include entire face in first screen-picture, it can also It to include part face, that is to say, the partial region of face.Electronic equipment can be according to different situations, using different processing Step specifically may refer to following step S22 to step S26, not repeat excessively first herein.

In step S22, electronic equipment obtains the face area and the face that face is located at except the first screen-picture Ratio.

After electronic equipment collects the first screen-picture, can analyze the face that first screen-picture includes is entire people Face or part face, if it is part face, that face is located at the face area except the first screen-picture in entire face Accounting be again how the case where, to based on the analysis results, be handled using different processing modes screen-picture, with Obtain the position of accurate target site.

The process that electronic equipment obtains the ratio can realize that being provided below two kinds can be able to achieve by different modes Mode, electronic equipment can use any mode, to acquire the ratio.

Mode one, electronic equipment carry out face critical point detection to first screen-picture, obtain the face be located at this The quantity of key point in one screen-picture obtains the difference of destination number and the quantity and the ratio of the destination number.

In mode one, which is the total quantity of the key point of face, the destination number and face be located at this The difference of the quantity of key point in one screen-picture is the number for the key point that the face is located at except first screen-picture Amount, which is located at the quantity of key point except the first screen-picture can use with the ratio of the total quantity of face key point It is located at the accounting of face area and entire face except the first screen-picture in expression face.

Mode two, electronic equipment carry out face critical point detection to first screen-picture, obtain the face be located at this The position of the edge key point of the position and face of key point in one screen-picture is located at first screen according to the face The position of the edge key point of the position and face of key point in picture, obtains the face and is located at first screen-picture The first area and second area for the first area that key point is surrounded, obtain the difference of the second area and first area with The ratio of the second area, the area for the second area which is surrounded for the edge key point.

In mode two, which can also directly calculate the face area that face is located at except the first screen-picture Area, carry out table using the ratio that the face is located at the area of the face area except the first screen-picture and the gross area of face Show the ratio.First area is the area that the face is located at the face area in the first screen-picture, and second area is the people The difference of the gross area of face, second area and the first area is the face for the face area that face is located at except the first screen-picture Product.

The above-mentioned possibility implementation for providing only two kinds of acquisition ratios, the electronic equipment can also come by other means The ratio is calculated, the embodiment of the present disclosure is not construed as limiting this.

In step S23, when the ratio meets goal condition, electronic equipment obtains target site in the second screen-picture First position and second screen-picture in include the target site first object region.

Electronic equipment get the face area that face is located at except the first screen-picture and entire face ratio it Afterwards, it can be determined that whether the ratio meets goal condition, when meeting goal condition, can directly use face by being different from The mode of recognizer obtains the position of target site.

In which, electronic equipment can first obtain of target site in the second screen-picture and the second screen-picture One position is drawn as the foundation for obtaining the second position of target site in the first screen-picture, then based on the first screen The situation of change of face in face and the second screen-picture, to obtain the second of target site in accurate first screen-picture It sets.

Wherein, first screen-picture and second screen-picture are the screen-picture collected different moments.At this Before step S23, which can first obtain the second screen-picture, the acquisition moment of second screen-picture and the first screen The acquisition moment of curtain picture is different, and specifically, the acquisition process of second screen-picture can be real by following any modes It is existing:

Mode one, electronic equipment obtain the former frame screen-picture of first screen-picture as second screen-picture.

Mode two, electronic equipment obtain the first frame screen-picture in collected multiframe screen-picture as second screen Curtain picture.

It is last less than the first proportion threshold value that mode three, electronic equipment obtain the ratio in collected multiframe screen-picture One frame screen-picture is as second screen-picture.

It should be noted that specifically can be by related skill as the second screen-picture using the screen-picture which acquires at moment Art personnel are configured according to demand, and the embodiment of the present disclosure is not construed as limiting this

In a kind of possible implementation, when the goal condition difference, step S22 can be different, specifically, the target Condition can be configured according to demand by related technical personnel, and the embodiment of the present disclosure is not construed as limiting this.It is provided below two kinds Possible goal condition, under different goal conditions, step S22 may include the possible implementation of following two:

In mode one, which may include obtaining mode, the first proportion threshold value and the second proportion threshold value, obtain When modulus formula is met certain condition and ratio is met certain condition, it can determine that the ratio meets goal condition.

Specifically, the second position that electronic equipment obtains target site in the first screen-picture can pass through two kinds of acquisition moulds Formula obtains, and that is to say, the first obtaining mode and the second obtaining mode.According to the difference of obtaining mode, which meets target The case where condition may include following two:

Situation one: when obtaining mode is first mode and the ratio is greater than the first proportion threshold value, the acquisition second is executed It include the first object region of the target site in the first position of target site and second screen-picture in screen-picture The step of, which is the mode that the second position is obtained based on recognition of face mode.

In situation one, current obtaining mode was directly using face identification method originally come the case where obtaining the second position Under, which is greater than the first proportion threshold value, illustrates face area that current face is located at except the first screen-picture in entire people Accounting in face is larger, that is to say, the face area in current first screen-picture account for it is smaller, directly use recognition of face side Formula is it is possible that the situation of recognition failures or inaccuracy is led to it is thereby possible to select that is to say using another obtaining mode Second mode is crossed to obtain the second position.In the second mode, electronic equipment can first obtain target in the second screen-picture The first position and first object region at position, to further determine that the position of image characteristic point becomes as foundation Change information and specifically may refer to following step S24 to step S26 to obtain the second position.

In the situation one, electronic equipment can also carry out the switching of obtaining mode, specifically, when obtaining mode is first When mode and the ratio are greater than the first proportion threshold value, electronic equipment can by the obtaining mode from the first mode switch to this Two modes.And then subsequent acquisition to screen-picture and is not necessarily in the case where switching obtaining mode again, can use second mould Formula obtains the second position.

Situation two: it when obtaining mode is second mode and the ratio is greater than the second proportion threshold value, executes and obtains the second screen It include the first object region of the target site in the first position of target site and second screen-picture in curtain picture Step, second proportion threshold value are less than first proportion threshold value, which is the change in location letter based on image characteristic point Breath obtains the mode of the second position.

In situation two, which is the ratio threshold that the mode that will acquire switches to first mode from second mode Value.It is to be appreciated that if when ratio is less than or equal to second proportion threshold value, it is believed that can be with using face identification method It is accurately obtained the position of target site, at this moment then can will acquire pattern switching to first mode without second mode. Thus, in the situation two, obtaining mode is second mode and ratio is greater than the second proportion threshold value, and electronic equipment is without being obtained Pattern switching is taken, then second mode can be directly used and obtain the second position, so that electronic equipment can execute in step S22 Acquisition first position and first object region the step of.

The ratio for being only located at the face area and the face except the first screen-picture in above-mentioned steps S23 to face meets The case where goal condition, is illustrated, which can also be unsatisfactory for goal condition, when the ratio is unsatisfactory for condition, electronics Equipment, which may not need, executes above-mentioned steps S23 and following step S24 to step S26, and electronic equipment can be to first screen Picture carries out recognition of face, obtains the second position of the target site in first screen-picture.

Specifically, two kinds of situations of goal condition are met corresponding to aforementioned proportion, in which one, which is unsatisfactory for The case where goal condition also may include following two:

Situation one: when obtaining mode is first mode and the ratio is less than or equal to the first proportion threshold value, electronic equipment Recognition of face is carried out to first screen-picture, obtains the second position of the target site in first screen-picture, this first Mode is that the mode of the second position is obtained based on recognition of face mode.

In situation one, current obtaining mode is first mode, when ratio is less than or equal to the first proportion threshold value, face position The accounting of face area in the first screen-picture is larger, directly can be accurately obtained target using face identification method The second position at position, thus, electronic equipment directly can carry out recognition of face to the first screen-picture.

Situation two: when obtaining mode is second mode and the ratio is less than or equal to the second proportion threshold value, electronic equipment Recognition of face is carried out to first screen-picture, obtains the second position of the target site in first screen-picture, this second Proportion threshold value is less than first proportion threshold value.

In situation two, current obtaining mode is second mode, and ratio is less than or equal to the second proportion threshold value, directly makes The second position of target site can be accurately obtained with the mode of recognition of face, electronic equipment can directly use recognition of face Mode obtain the second position.

In a kind of possible implementation, in situation two, current obtaining mode and ratio meet obtaining mode switching Condition, electronic equipment can also carry out the switching of obtaining mode.Specifically, when obtaining mode is second mode and the ratio is less than Or when being equal to the second proportion threshold value, electronic equipment can will acquire mode and switch to the first mode from the second mode.

In aforesaid way one, the proportion threshold value that the first proportion threshold value and the second proportion threshold value switch for obtaining mode, In the case that obtaining mode is first mode, pattern switching can be will acquire to second if ratio is greater than the first proportion threshold value Mode if ratio is less than or equal to the second proportion threshold value, can will be obtained in the case where obtaining mode is second mode Modulus formula switches to first mode.It should be noted that first proportion threshold value and the second proportion threshold value can be by the relevant technologies Personnel are configured according to demand, for example, first proportion threshold value is 0.7, the second proportion threshold value is 0.5, the embodiment of the present disclosure This is not construed as limiting.

For example, in a specific example, with the first proportion threshold value for 0.7, for the second proportion threshold value is 0.5, electronics Equipment collects multiple screen-pictures, the variation tendency of the aforementioned proportion of multiple screen-picture are as follows: it is changed to 0.8 from 0.4, from 0.8 is changed to 0.4 again.By the setting of above-mentioned goal condition, during ratio is changed to 0.7 from 0.4, electronic equipment can To use first mode, directly progress recognition of face obtains the second position.During ratio is changed to 0.8 from 0.7, electricity Sub- equipment can use second mode, need auxiliary by the data of the second screen-picture and the change in location information of image characteristic point It helps, obtains the second position.During ratio is changed to 0.5 from 0.8, electronic equipment can use second mode, in ratio From 0.5 be changed to 0.4 during, electronic equipment can use first mode.

In a kind of possible implementation, in which one, a kind of smooth transition mode can also be set, obtained at two kinds In mode handover procedure, another obtaining mode smoothly can be switched to from a kind of obtaining mode, improve got The phenomenon that flatness of two positions is not in jump, recognition effect is more preferable.Specifically, which may include The following three steps:

Step 1: when obtaining mode is first mode and the ratio is greater than the first proportion threshold value, or, when obtaining mode is When second mode and the ratio are less than or equal to the second proportion threshold value, electronic equipment carries out face knowledge to first screen-picture Not, the third place of the target site in first screen-picture is obtained.

Step 2: electronic equipment executes first position, the first object region for obtaining target site in the second screen-picture The step of with change in location information, obtains the mesh in first screen-picture based on the first position and the change in location information Mark the 4th position at position.

Step 3: electronic equipment is based on the third place and the 4th position, the target in first screen-picture is obtained The second position at position.

In the step 3, electronic equipment can integrate by weighted summation it is that two kinds of processing modes obtain as a result, Specifically, electronic equipment can be weighted summation to the third place and the 4th position, obtain in first screen-picture The second position of the target site.

Wherein, the third place and the weight of the 4th position can be configured according to demand by related technical personnel, The method of determination of the weight can also be set by related technical personnel.

In a kind of possible implementation, the weight of the third place and the 4th position can be based on the ratio and first The relationship of proportion threshold value determines, for example, weight of the first difference of first proportion threshold value and the ratio as the third place, it will Weight of 1 the second difference obtained with the difference as the 4th position, it is, of course, also possible to be arranged by other means, this public affairs It opens embodiment and this is not construed as limiting.

In alternatively possible implementation, the weight of the third place and the 4th position can also based on the ratio with The relationship of second proportion threshold value determines.The set-up mode and a kind of upper implementation similarly, do not repeat excessively herein.

In another possible implementation, the weight of the third place and the 4th position be based on present system time with The relationship of pattern switching duration determines.For example, a length of T when switching can be set, is t in present system time, T-t can be made For the weight of the third place, using t as the weight of the 4th position.

Be illustrated above by a kind of a pair of goal condition setting of mode, below to another goal condition be arranged into Row explanation.In mode two, it is directly the first proportion threshold value of ratio setting and the second proportion threshold value, passes through ratio and two ratios The relationship of threshold value, to determine that two kinds of processing modes and above two obtaining mode are similarly using which kind of processing mode.

In mode two, step S23 can be with are as follows: when the ratio is greater than the first proportion threshold value, executes the acquisition second It include the first object region of the target site in the first position of target site and second screen-picture in screen-picture The step of.Ratio is greater than the first proportion threshold value, and the face area accounting for illustrating that face is located at except screen-picture is larger, needs to lead to Cross the data of the second screen-picture and the change in location information auxiliary of image characteristic point.It is also proportional discontented in which two The case where foot-eye condition, the situation can be with are as follows: when the ratio is less than or equal to the second proportion threshold value, electronic equipment to this One screen-picture carries out recognition of face, obtains the second position of the target site in first screen-picture.

It should be noted that first proportion threshold value and the second proportion threshold value can by related technical personnel according to demand into Row setting, first proportion threshold value can be greater than or equal to the second proportion threshold value.First proportion threshold value and the second proportion threshold value Size relation difference when, which can be with different.

In a kind of possible implementation, which can be identical as second proportion threshold value.In this feelings Under condition, the case where which is unsatisfactory for goal condition, can be with are as follows: when the ratio is less than or equal to first proportion threshold value, electronics Equipment executes this and carries out recognition of face to first screen-picture, obtains the second of the target site in first screen-picture The step of setting.

In alternatively possible implementation, which can be greater than second proportion threshold value.In this reality In existing mode, which is likely less than the first proportion threshold value, and be greater than second proportion threshold value can be set in this case Have: while using two kinds of processing modes, then comprehensive two kinds of processing modes as a result, obtaining the second position.Specifically, in the situation May include the following three steps:

Step 1: when the ratio be less than first proportion threshold value, and the ratio be greater than second proportion threshold value when, electronics is set It is standby to execute the step of this carries out recognition of face to first screen-picture, obtain the of the target site in first screen-picture Three positions.

Smooth transition mode of the step 1 into step 3 and aforesaid way one is similarly, full needed for the ratio being only arranged The condition of foot is different.It should be noted that passing through the setting of two kinds of processing modes of synthesis, can switch in two kinds of processing modes During the intermediate handoff procedure of setting one, so as to by the intermediate handoff procedure, so that two kinds of processing modes are smooth The phenomenon that flatness of transition, the second position obtained in this way is more preferable, is not in jump, so that recognition effect is more preferable.

In step s 24, electronic equipment carries out feature extraction to the first object region and second target area respectively, Obtain the position of the position of the first image characteristic point and the second image characteristic point in second target area in the first object region It sets.

Wherein, which is that the first object region is corresponding including the target in second screen-picture The region at position.

Electronic equipment can track it after getting first object region, obtain the second target area, pass through The variation of image characteristic point in first object region and the second target area, to determine that the second screen-picture is changed to the first screen When picture, the situation of change of face, and then can be calculated according to the first position of target site in the second screen-picture The second position of target site in one screen-picture.

In a kind of possible implementation, the quantity of first image characteristic point and the second image characteristic point can be more A, then step S24 can be with are as follows: electronic equipment carries out feature to the first object region and second target area respectively and mentions It takes, obtains the position of multiple first image characteristic points and multiple second images in second target area in the first object region The position of characteristic point.

In step s 25, the position of the electronic equipment position based on first image characteristic point and second image characteristic point It sets, obtains the change in location information.

Electronic equipment can integrate two behind the position of the position and the second image characteristic point that obtain the first image characteristic point A position, come when determining that the second screen-picture is changed to the first screen-picture, the situation of change of face be that is to say, which becomes Change information.

It, can be by the position of the position of the second image characteristic point and the first image characteristic point in a kind of possible implementation Difference as the change in location information.

In a kind of possible implementation, the quantity of first image characteristic point and the second image characteristic point can be more A, then step S25 can be with are as follows: electronic equipment can be according to the position of the first image characteristic points multiple in the first object region With the position of the second image characteristic points multiple in second target area, multiple first image characteristic point and multiple the are obtained Mean place change information between two image characteristic points, using the mean place change information as the first object region and The change in location information of image characteristic point in two target areas.

It should be noted that above-mentioned steps S24 and step S25 are obtained in the first object region and the second target area The process of the change in location information of image characteristic point, above-mentioned steps S24 and step S25 only show a kind of implementation, the process It can also realize by other means, for example, electronic equipment can carry out first screen-picture and second screen-picture Matching obtains the similarity in first object region and the second target area in second screen-picture in first screen-picture, Based on the similarity, the change in location information of image characteristic point in the first object region and second target area is obtained.

In step S26, electronic equipment is based on the first position and the change in location information, obtains first screen-picture In the target site the second position.

Specifically, the available first position of electronic equipment and the second position change information and value, by this and value The second position as the target site in first screen-picture.Electronic equipment is according to target site in the second screen-picture Position is obtained in analysis in two screen-pictures after the situation of change of face, in raw bits as home position (first position) On the basis of setting, the available second position.

For example, the acquisition process of the second position can be realized by following formula:

Pnew=Porigin+1/m* (P1 '+P2 '+...+Pm '-(P1+P2+ ...+Pm))

Pnew is the second position, and Porigin is first position, and P1, P2 ... Pm are the position of the first image characteristic point, P1 ', P2 ' ... Pm ' is the position of the second image characteristic point.

In a kind of possible implementation, after step S26, which can also be according to first screen-picture In the target site the second position, obtain the target position of virtual objects.For example, the virtual objects can be virtual ornaments, Behind the position for determining face position, it can be scaled the position of virtual ornaments, add the image of virtual ornaments.

The ratio is not considered in the related technology, under any circumstance directly by face recognition algorithms come to screen-picture Recognition of face is carried out, it is possible that recognition failures, inaccuracy etc. are asked in the case where only including part face in screen-picture Topic, and present disclose provides different processing modes, in the case where only including part face in screen-picture, by analyzing people The situation of change of face carries out change in location based on accurately home position, obtains the accurate second position.

Fig. 3 is a kind of position acquisition device block diagram at face position shown according to an exemplary embodiment.Reference Fig. 3, The device includes:

Ratio acquisition unit 301, be configured as executing obtain face be located at face area except the first screen-picture and The ratio of the face；

Position acquisition unit 302 is configured as executing when the ratio meets goal condition, obtain in the second screen-picture It include the first object region of the target site, first screen in the first position of target site and second screen-picture Picture and second screen-picture are the screen-picture collected different moments；

It is special to be configured as executing image in the acquisition first object region and the second target area for information acquisition unit 303 The change in location information of point is levied, which, which is that the first object region is corresponding in second screen-picture, includes The region of the target site；

The position acquisition unit 302 is additionally configured to execute based on the first position and the change in location information, and obtaining should The second position of the target site in first screen-picture.

In a kind of possible implementation, which is configured as executing any one of following:

In a kind of possible implementation, which is configured as executing respectively to the first object area Domain and second target area carry out feature extraction, obtain in the first object region position of multiple first image characteristic points and The position of multiple second image characteristic points in second target area；

The information acquisition unit 303 is configured as executing according to the first image characteristic points multiple in the first object region The position of multiple second image characteristic points in position and second target area, obtains multiple first image characteristic point and this is more Mean place change information between a second image characteristic point, using the mean place change information as the first object region With the change in location information of image characteristic point in the second target area.

In a kind of possible implementation, which is additionally configured to execute when obtaining mode is first When mode and the ratio are greater than the first proportion threshold value, which is switched into the second mode from the first mode.

In a kind of possible implementation, which is additionally configured to execute any one of following:

In a kind of possible implementation, the device further include:

First mode switch unit is configured as executing when obtaining mode is that second mode and the ratio are less than or equal to the When two proportion threshold values, it will acquire mode from the second mode and switch to the first mode.

In a kind of possible implementation, which is additionally configured to execute:

In a kind of possible implementation, which is configured as executing when the ratio is greater than the first ratio When example threshold value, execute in second screen-picture of acquisition include in the first position of target site and second screen-picture should The step of first object region of target site；

The position acquisition unit 302 is additionally configured to execute when the ratio is less than or equal to the second proportion threshold value, to this First screen-picture carries out recognition of face, obtains the second position of the target site in first screen-picture.

The position acquisition unit 302 is configured as executing when the ratio is less than or equal to first proportion threshold value, executes This carries out recognition of face to first screen-picture, obtains the step of the second position of the target site in first screen-picture Suddenly.

The position acquisition unit 302 is configured as executing:

In a kind of possible implementation, the position acquisition unit 302 be configured as executing to the third place and this Four positions are weighted summation, obtain the second position of the target site in first screen-picture.

In a kind of possible implementation, which, which is configured as executing, obtains the first position and is somebody's turn to do Second position change information and value, the second position by this and value as the target site in first screen-picture.

In a kind of possible implementation, which further includes picture acquiring unit, which is configured as It executes any one of following:

About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method Embodiment in be described in detail, no detailed explanation will be given here.

Above-mentioned electronic equipment can be following terminals shown in Fig. 4, or following servers shown in fig. 5, this public affairs It opens embodiment and this is not construed as limiting.

Fig. 4 is a kind of structural block diagram of terminal shown according to an exemplary embodiment.The terminal 400 may is that intelligence Mobile phone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic image Expert's compression standard audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic shadow As expert's compression standard audio level 4) player, laptop or desktop computer.Terminal 400 is also possible to referred to as user and sets Other titles such as standby, portable terminal, laptop terminal, terminal console.

In general, terminal 400 includes: processor 401 and memory 402.

Processor 401 may include one or more processing cores, such as 4 core processors, 8 core processors etc..Place Reason device 401 can use DSP (Digital Signal Processing, Digital Signal Processing), FPGA (Field- Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array, may be programmed Logic array) at least one of example, in hardware realize.Processor 401 also may include primary processor and coprocessor, master Processor is the processor for being handled data in the awake state, also referred to as CPU (Central Processing Unit, central processing unit)；Coprocessor is the low power processor for being handled data in the standby state.? In some embodiments, processor 401 can be integrated with GPU (Graphics Processing Unit, image processor), GPU is used to be responsible for the rendering and drafting of content to be shown needed for display screen.In some embodiments, processor 401 can also be wrapped AI (Artificial Intelligence, artificial intelligence) processor is included, the AI processor is for handling related machine learning Calculating operation.

Memory 402 may include one or more computer readable storage mediums, which can To be non-transient.Memory 402 may also include high-speed random access memory and nonvolatile memory, such as one Or multiple disk storage equipments, flash memory device.In some embodiments, the non-transient computer in memory 402 can Storage medium is read for storing at least one instruction, at least one instruction for performed by processor 401 to realize this public affairs Open the location acquiring method at the face position that middle embodiment of the method provides.

In some embodiments, terminal 400 is also optional includes: peripheral device interface 403 and at least one peripheral equipment. It can be connected by bus or signal wire between processor 401, memory 402 and peripheral device interface 403.Each peripheral equipment It can be connected by bus, signal wire or circuit board with peripheral device interface 403.Specifically, peripheral equipment includes: radio circuit 404, at least one of touch display screen 405, camera 406, voicefrequency circuit 407, positioning component 408 and power supply 409.

Peripheral device interface 403 can be used for I/O (Input/Output, input/output) is relevant outside at least one Peripheral equipment is connected to processor 401 and memory 402.In some embodiments, processor 401, memory 402 and peripheral equipment Interface 403 is integrated on same chip or circuit board；In some other embodiments, processor 401, memory 402 and outer Any one or two in peripheral equipment interface 403 can realize on individual chip or circuit board, the present embodiment to this not It is limited.

Radio circuit 404 is for receiving and emitting RF (Radio Frequency, radio frequency) signal, also referred to as electromagnetic signal.It penetrates Frequency circuit 404 is communicated by electromagnetic signal with communication network and other communication equipments.Radio circuit 404 turns electric signal It is changed to electromagnetic signal to be sent, alternatively, the electromagnetic signal received is converted to electric signal.Optionally, radio circuit 404 wraps It includes: antenna system, RF transceiver, one or more amplifiers, tuner, oscillator, digital signal processor, codec chip Group, user identity module card etc..Radio circuit 404 can be carried out by least one wireless communication protocol with other terminals Communication.The wireless communication protocol includes but is not limited to: Metropolitan Area Network (MAN), each third generation mobile communication network (2G, 3G, 4G and 5G), wireless office Domain net and/or WiFi (Wireless Fidelity, Wireless Fidelity) network.In some embodiments, radio circuit 404 may be used also To include the related circuit of NFC (Near Field Communication, wireless near field communication), the disclosure is not subject to this It limits.

Display screen 405 is for showing UI (User Interface, user interface).The UI may include figure, text, figure Mark, video and its their any combination.When display screen 405 is touch display screen, display screen 405 also there is acquisition to show The ability of the touch signal on the surface or surface of screen 405.The touch signal can be used as control signal and be input to processor 401 are handled.At this point, display screen 405 can be also used for providing virtual push button and/or dummy keyboard, also referred to as soft button and/or Soft keyboard.In some embodiments, display screen 405 can be one, and the front panel of terminal 400 is arranged；In other embodiments In, display screen 405 can be at least two, be separately positioned on the different surfaces of terminal 400 or in foldover design；In still other reality It applies in example, display screen 405 can be flexible display screen, be arranged on the curved surface of terminal 400 or on fold plane.Even, it shows Display screen 405 can also be arranged to non-rectangle irregular figure, namely abnormity screen.Display screen 405 can use LCD (Liquid Crystal Display, liquid crystal display), OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) Etc. materials preparation.

CCD camera assembly 406 is for acquiring image or video.Optionally, CCD camera assembly 406 include front camera and Rear camera.In general, the front panel of terminal is arranged in front camera, the back side of terminal is arranged in rear camera.One In a little embodiments, rear camera at least two is main camera, depth of field camera, wide-angle camera, focal length camera shooting respectively Any one in head, to realize that main camera and the fusion of depth of field camera realize background blurring function, main camera and wide-angle Camera fusion realizes that pan-shot and VR (Virtual Reality, virtual reality) shooting function or other fusions are clapped Camera shooting function.In some embodiments, CCD camera assembly 406 can also include flash lamp.Flash lamp can be monochromatic warm flash lamp, It is also possible to double-colored temperature flash lamp.Double-colored temperature flash lamp refers to the combination of warm light flash lamp and cold light flash lamp, can be used for not With the light compensation under colour temperature.

Voicefrequency circuit 407 may include microphone and loudspeaker.Microphone is used to acquire the sound wave of user and environment, and will Sound wave, which is converted to electric signal and is input to processor 401, to be handled, or is input to radio circuit 404 to realize voice communication. For stereo acquisition or the purpose of noise reduction, microphone can be separately positioned on the different parts of terminal 400 to be multiple.Mike Wind can also be array microphone or omnidirectional's acquisition type microphone.Loudspeaker is then used to that processor 401 or radio circuit will to be come from 404 electric signal is converted to sound wave.Loudspeaker can be traditional wafer speaker, be also possible to piezoelectric ceramic loudspeaker.When When loudspeaker is piezoelectric ceramic loudspeaker, the audible sound wave of the mankind can be not only converted electrical signals to, it can also be by telecommunications Number the sound wave that the mankind do not hear is converted to carry out the purposes such as ranging.In some embodiments, voicefrequency circuit 407 can also include Earphone jack.

Positioning component 408 is used for the current geographic position of positioning terminal 400, to realize navigation or LBS (Location Based Service, location based service).Positioning component 408 can be the GPS (Global based on the U.S. Positioning System, global positioning system), the dipper system of China, Russia Gray receive this system or European Union The positioning component of Galileo system.

Power supply 409 is used to be powered for the various components in terminal 400.Power supply 409 can be alternating current, direct current, Disposable battery or rechargeable battery.When power supply 409 includes rechargeable battery, which can support wired charging Or wireless charging.The rechargeable battery can be also used for supporting fast charge technology.

In some embodiments, terminal 400 further includes having one or more sensors 410.The one or more sensors 410 include but is not limited to: acceleration transducer 411, gyro sensor 412, pressure sensor 413, fingerprint sensor 414, Optical sensor 415 and proximity sensor 416.

The acceleration that acceleration transducer 411 can detecte in three reference axis of the coordinate system established with terminal 400 is big It is small.For example, acceleration transducer 411 can be used for detecting component of the acceleration of gravity in three reference axis.Processor 401 can With the acceleration of gravity signal acquired according to acceleration transducer 411, touch display screen 405 is controlled with transverse views or longitudinal view Figure carries out the display of user interface.Acceleration transducer 411 can be also used for the acquisition of game or the exercise data of user.

Gyro sensor 412 can detecte body direction and the rotational angle of terminal 400, and gyro sensor 412 can To cooperate with acquisition user to act the 3D of terminal 400 with acceleration transducer 411.Processor 401 is according to gyro sensor 412 Following function may be implemented in the data of acquisition: when action induction (for example changing UI according to the tilt operation of user), shooting Image stabilization, game control and inertial navigation.

The lower layer of side frame and/or touch display screen 405 in terminal 400 can be set in pressure sensor 413.Work as pressure When the side frame of terminal 400 is arranged in sensor 413, user can detecte to the gripping signal of terminal 400, by processor 401 Right-hand man's identification or prompt operation are carried out according to the gripping signal that pressure sensor 413 acquires.When the setting of pressure sensor 413 exists When the lower layer of touch display screen 405, the pressure operation of touch display screen 405 is realized to UI circle according to user by processor 401 Operability control on face is controlled.Operability control includes button control, scroll bar control, icon control, menu At least one of control.

Fingerprint sensor 414 is used to acquire the fingerprint of user, collected according to fingerprint sensor 414 by processor 401 The identity of fingerprint recognition user, alternatively, by fingerprint sensor 414 according to the identity of collected fingerprint recognition user.It is identifying When the identity of user is trusted identity out, the user is authorized to execute relevant sensitive operation, the sensitive operation packet by processor 401 Include solution lock screen, check encryption information, downloading software, payment and change setting etc..Terminal can be set in fingerprint sensor 414 400 front, the back side or side.When being provided with physical button or manufacturer Logo in terminal 400, fingerprint sensor 414 can be with It is integrated with physical button or manufacturer Logo.

Optical sensor 415 is for acquiring ambient light intensity.In one embodiment, processor 401 can be according to optics The ambient light intensity that sensor 415 acquires controls the display brightness of touch display screen 405.Specifically, when ambient light intensity is higher When, the display brightness of touch display screen 405 is turned up；When ambient light intensity is lower, the display for turning down touch display screen 405 is bright Degree.In another embodiment, the ambient light intensity that processor 401 can also be acquired according to optical sensor 415, dynamic adjust The acquisition parameters of CCD camera assembly 406.

Proximity sensor 416, also referred to as range sensor are generally arranged at the front panel of terminal 400.Proximity sensor 416 For acquiring the distance between the front of user Yu terminal 400.In one embodiment, when proximity sensor 416 detects use When family and the distance between the front of terminal 400 gradually become smaller, touch display screen 405 is controlled from bright screen state by processor 401 It is switched to breath screen state；When proximity sensor 416 detects user and the distance between the front of terminal 400 becomes larger, Touch display screen 405 is controlled by processor 401 and is switched to bright screen state from breath screen state.

It will be understood by those skilled in the art that the restriction of the not structure paired terminal 400 of structure shown in Fig. 4, can wrap It includes than illustrating more or fewer components, perhaps combine certain components or is arranged using different components.

Fig. 5 is a kind of structural schematic diagram of server shown according to an exemplary embodiment, which can be because matching It sets or performance is different and generate bigger difference, may include one or more processors (central Processing units, CPU) 501 and one or more memory 502, wherein it is stored in the memory 502 At least one instruction, at least one instruction are loaded by the processor 501 and are executed to realize that above-mentioned each embodiment of the method mentions The location acquiring method at the face position of confession.Certainly, the server can also have wired or wireless network interface, keyboard and The components such as input/output interface, to carry out input and output, which can also include other for realizing functions of the equipments Component, this will not be repeated here.

In the exemplary embodiment, a kind of storage medium including instruction is additionally provided, the memory for example including instruction, Above-metioned instruction can be executed by the processor of device to complete the location acquiring method at above-mentioned face position.Optionally, storage medium Can be non-transitorycomputer readable storage medium, for example, the non-transitorycomputer readable storage medium can be it is read-only Memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), read-only light Disk (Compact Disc Read-Only Memory, CD-ROM), tape, floppy disk and optical data storage devices etc..

In the exemplary embodiment, a kind of computer program product is additionally provided, including one or more instructs, this Or a plurality of instruction can be executed by the processor of electronic equipment, be obtained with completing the position at the face position provided in above-described embodiment Take the method and step of method.

Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following Claim is pointed out.

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

Claims

1. a kind of location acquiring method at face position characterized by comprising

When the ratio meets goal condition, the first position and described second of target site in the second screen-picture is obtained It include the first object region of the target site in screen-picture, first screen-picture and second screen-picture are The screen-picture that different moments collect；

Obtain the change in location information of image characteristic point in the first object region and the second target area, second target Region is the first object region corresponding region including the target site in second screen-picture；

Based on the first position and the change in location information, the of target site described in first screen-picture is obtained Two positions.

2. the location acquiring method at face position according to claim 1, which is characterized in that the acquisition face is located at the The ratio of face area and the face except one screen-picture, including any one of following:

Face critical point detection is carried out to first screen-picture, the face is obtained and is located in first screen-picture The quantity of key point obtains the difference of destination number and the quantity and the ratio of the destination number；

Face critical point detection is carried out to first screen-picture, the face is obtained and is located in first screen-picture The position of the edge key point of the position of key point and the face is located in first screen-picture according to the face The position of the edge key point of the position of key point and the face obtains the pass that the face is located at first screen-picture The first area and second area for the first area that key point is surrounded, obtain the difference of the second area Yu first area The area of the second area surrounded with the ratio of the second area, the second area by the edge key point.

3. the location acquiring method at face position according to claim 1, which is characterized in that described to obtain first mesh The change in location information of image characteristic point in region and the second target area is marked, including any one of following:

Feature extraction is carried out to the first object region and second target area respectively, obtains the first object region In the first image characteristic point position and second target area in the second image characteristic point position, be based on first figure As the position of characteristic point and the position of second image characteristic point, the change in location information is obtained；

First screen-picture and second screen-picture are matched, the first mesh in first screen-picture is obtained The similarity of the second target area in region and second screen-picture is marked, the similarity is based on, obtains first mesh Mark the change in location information of image characteristic point in region and second target area.

4. the location acquiring method at face position according to claim 3, which is characterized in that described respectively to described first Target area and second target area carry out feature extraction, obtain the first image characteristic point in the first object region The position of second image characteristic point in position and second target area, comprising:

Feature extraction is carried out to the first object region and second target area respectively, obtains the first object region In multiple first image characteristic points position and second target area in multiple second image characteristic points position；

The position of the position based on the first image characteristic point and second image characteristic point obtains the position and becomes Change information, comprising:

According in the position and second target area of the first image characteristic points multiple in the first object region multiple The position of two image characteristic points obtains flat between the multiple first image characteristic point and the multiple second image characteristic point Equal change in location information, using the mean place change information as image in the first object region and the second target area The change in location information of characteristic point.

5. the location acquiring method at face position according to claim 1, which is characterized in that described when the ratio meets When goal condition, it includes described for obtaining in the second screen-picture in the first position of target site and second screen-picture The first object region of target site, including any one of following:

When obtaining mode is first mode and the ratio is greater than the first proportion threshold value, the second screen-picture of the acquisition is executed The step in the first object region in the first position of middle target site and second screen-picture including the target site Suddenly, the first mode is the mode that the second position is obtained based on recognition of face mode；

When obtaining mode is second mode and the ratio is greater than the second proportion threshold value, executes and obtain mesh in the second screen-picture Mark the first object region for including the steps that the target site in the first position and second screen-picture at position, institute The second proportion threshold value is stated less than first proportion threshold value, the second mode is the change in location information based on image characteristic point Obtain the mode of the second position.

6. the location acquiring method at face position according to claim 1, which is characterized in that the acquisition face is located at the Face area except one screen-picture and after the ratio of the face, the method also includes any one of following:

When obtaining mode is first mode and the ratio is less than or equal to the first proportion threshold value, to first screen-picture Carry out recognition of face, obtain the second position of target site described in first screen-picture, the first mode be based on Recognition of face mode obtains the mode of the second position；

When obtaining mode is second mode and the ratio is less than or equal to the second proportion threshold value, to first screen-picture Recognition of face is carried out, obtains the second position of target site described in first screen-picture, second proportion threshold value is small In first proportion threshold value, the second mode is the mould of the change in location acquisition of information second position based on image characteristic point Formula.

7. the location acquiring method at face position according to claim 5 or 6, which is characterized in that the method also includes:

When obtaining mode is first mode and the ratio is greater than the first proportion threshold value, or, when obtaining mode is second mode And the ratio carries out recognition of face to first screen-picture, obtains described the when being less than or equal to the second proportion threshold value The third place of target site described in one screen-picture；

Execute the step for obtaining the first position, first object region and change in location information of target site in the second screen-picture Suddenly, it is based on the first position and the change in location information, obtains the of target site described in first screen-picture Four positions；

Based on the third place and the 4th position, the second of target site described in first screen-picture is obtained It sets.

8. a kind of position acquisition device at face position characterized by comprising

Ratio acquisition unit is configured as executing the face area and the face for obtaining that face is located at except the first screen-picture Ratio；

Position acquisition unit is configured as executing when the ratio meets goal condition, obtains target in the second screen-picture It include the first object region of the target site, first screen in the first position at position and second screen-picture Curtain picture and second screen-picture are the screen-picture collected different moments；

Information acquisition unit is configured as executing image characteristic point in the acquisition first object region and the second target area Change in location information, second target area, which is that the first object region is corresponding in second screen-picture, includes The region of the target site；

The position acquisition unit is additionally configured to execute based on the first position and the change in location information, obtains institute State the second position of target site described in the first screen-picture.

9. a kind of electronic equipment characterized by comprising

One or more processors；

Wherein, one or more of processors are configured as executing described instruction, to realize as any in claim 1 to 7 The location acquiring method at the face position described in.

10. a kind of storage medium, which is characterized in that when the instruction in the storage medium is executed by the processor of electronic equipment When, so that the electronic equipment is able to carry out the position acquisition side at the face position as described in any one of claims 1 to 7 Method.