CN106791535A - Video recording method and device - Google Patents
Video recording method and device Download PDFInfo
- Publication number
- CN106791535A CN106791535A CN201611071695.8A CN201611071695A CN106791535A CN 106791535 A CN106791535 A CN 106791535A CN 201611071695 A CN201611071695 A CN 201611071695A CN 106791535 A CN106791535 A CN 106791535A
- Authority
- CN
- China
- Prior art keywords
- field picture
- facial characteristics
- video
- record
- mask
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 230000001815 facial effect Effects 0.000 claims abstract description 181
- 230000014509 gene expression Effects 0.000 claims description 43
- 210000004709 eyebrow Anatomy 0.000 claims description 7
- 241000406668 Loxodonta cyclotis Species 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 32
- 238000010586 diagram Methods 0.000 description 22
- 238000012545 processing Methods 0.000 description 19
- 230000006870 function Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 230000008921 facial expression Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 7
- 210000000887 face Anatomy 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000000712 assembly Effects 0.000 description 3
- 238000000429 assembly Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000005538 encapsulation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000012092 media component Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
Landscapes
- Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The present invention relates to a kind of video recording method and device, wherein the method includes：Each two field picture of the video to being played carries out facial characteristics identification frame by frame；The position for recording mask and size in each two field picture are determined according to facial characteristics recognition result；And position according to the record mask in each two field picture and size are recorded to the video.According to the video recording method and device of the embodiment of the present disclosure, record screen technology is applied to by by facial characteristics identification technology, position and size thus, it is possible to flexibly set record mask, so as to record out the desired video of user, improve Consumer's Experience.
Description
Technical field
The present invention relates to image processing field, more particularly to a kind of video recording method and device.
Background technology
For the Online Video or local video at PC (Personal Computer, personal computer) ends, regarded in current
Frequency is recorded (be also known as below " record screen ") in technology, and the frame bit selecting for recording mask is put fixed and is only capable of recording regarding in fixed range
Frequency content, i.e. the frame bit selecting of record mask are put and size is fixed.Thus, causing to record the video content for obtaining not always to use
Family is desired, and user experience is poor.
The content of the invention
In view of this, recorded by the way that facial characteristics identification technology to be applied to the video of record screen technology the present disclosure proposes a kind of
Method and apparatus processed.Thereby, it is possible to flexibly set position and the size of record mask, so that the desired video of user is recorded out,
Improve Consumer's Experience.
According to the one side of the disclosure, there is provided a kind of video recording method, including：Each frame figure of the video to being played
As carrying out facial characteristics identification frame by frame；The position of the record mask in each two field picture is determined according to facial characteristics recognition result
Put and size；And position according to the record mask in each two field picture and size are recorded to the video.
For above-mentioned video recording method, in a kind of possible implementation, according to facial characteristics recognition result come really
The position of the record mask being scheduled in each two field picture and size, including：Determined described according to facial characteristics recognition result
The position of the record mask in each two field picture and original dimension；One of size is selected to make from each original dimension determined
On the basis of size；And the original dimension of the record mask in each two field picture is adjusted to the reference dimension.
For above-mentioned video recording method, in a kind of possible implementation, the reference dimension is regarded according to
The resolution ratio of each two field picture of frequency and pre-set.
For above-mentioned video recording method, in a kind of possible implementation, according to facial characteristics recognition result come really
The position of the record mask being scheduled in each two field picture and size, including：Recognized from a two field picture of the video first
In the case of going out the facial characteristics of multiple objects, at least one object is selected from the multiple object as perpetual object；
In the follow-up two field picture of one two field picture, the similarity with the facial characteristics of each object in the perpetual object is determined frame by frame
The matching facial characteristics of the corresponding objects below predetermined similarity threshold respectively；And respectively according in the perpetual object
The facial characteristics of each object and the matching facial characteristics of each corresponding objects determine in a two field picture and the subsequent frame
The position of the record mask in image and size.
For above-mentioned video recording method, in a kind of possible implementation, also include：Continue two field picture in the rear
In, if there is the two field picture without the matching facial characteristics, then each object respectively in the perpetual object
The matching facial characteristics of facial characteristics and each corresponding objects is special to not having the matching face from a two field picture to determine
The position of the record mask in the two field picture between the two field picture levied and size.
For above-mentioned video recording method, in a kind of possible implementation, respectively according in the perpetual object
The matching facial characteristics of the facial characteristics of each object and each corresponding objects determines in a two field picture and the subsequent frame figure
The position of the record mask as in and size, including：The facial characteristics of each object in the perpetual object and each right respectively
Tackle elephant matching facial characteristics come determine in a two field picture and the follow-up two field picture record mask position and just
Beginning size；One of size is selected from each original dimension determined as reference dimension；And will be in a frame
Original dimension in image and the follow-up two field picture is adjusted to the reference dimension.
For above-mentioned video recording method, in a kind of possible implementation, the reference dimension is regarded according to
The resolution ratio of each two field picture of frequency and pre-set.
For above-mentioned video recording method, in a kind of possible implementation, according to the record in each two field picture
The position of mask and size are recorded to the video, including：Default expression is loaded into the record mask；And
The position of the record mask according to the expression for being loaded and in each two field picture and size are recorded to the video.
For above-mentioned video recording method, in a kind of possible implementation, each two field picture of the video to being played
Facial characteristics identification is carried out frame by frame, including：Facial critical zone locations in each two field picture of the video played are carried out
Positioning, wherein, the critical zone locations are included in eyebrow, eyes, nose, face, ear and face mask region
At least one.
According to another aspect of the present disclosure, there is provided a kind of video recording device, including：Facial characteristics recognition unit, uses
Facial characteristics identification is carried out frame by frame in each two field picture of the video to being played；Determining unit, recognizes single with the facial characteristics
Unit's connection, position and size for determining the record mask in each two field picture according to facial characteristics recognition result；With
And record screen unit, be connected with the determining unit, for basis in each two field picture record mask position and size come
The video is recorded.
For above-mentioned video recording device, in a kind of possible implementation, the determining unit includes：First determines
Module, position and original dimension for determining the record mask in each two field picture according to facial characteristics recognition result；
First choice module, is connected with first determining module, for selecting one of them from each original dimension determined
Size is used as reference dimension；And adjusting module, it is connected with the first choice module, for by each two field picture
The original dimension for recording mask is adjusted to the reference dimension.
For above-mentioned video recording device, in a kind of possible implementation, the reference dimension is regarded according to
The resolution ratio of each two field picture of frequency and pre-set.
For above-mentioned video recording device, in a kind of possible implementation, the determining unit includes：Second selection
Module, in the case of the facial characteristics that multiple objects are identified from a two field picture of the video first, from described
At least one object is selected in multiple objects as perpetual object；Second determining module, is connected with second selecting module, uses
In the follow-up two field picture in a two field picture, the phase with the facial characteristics of each object in the perpetual object is determined frame by frame
Like the matching facial characteristics of degree corresponding objects respectively below predetermined similarity threshold；And the 3rd determining module, with institute
The connection of the second determining module is stated, the facial characteristics and each corresponding objects for each object respectively in the perpetual object
Facial characteristics is matched to determine position and the size of the record mask in a two field picture and the follow-up two field picture.
For above-mentioned video recording device, in a kind of possible implementation, the 3rd determining module is additionally operable to：
It is if there is the two field picture without the matching facial characteristics, then right according to the concern respectively in the follow-up two field picture
The facial characteristics of each object as in and the matching facial characteristics of each corresponding objects determine from a two field picture to not having
The position of the record mask in two field picture between the two field picture of the matching facial characteristics and size.
For above-mentioned video recording device, in a kind of possible implementation, the 3rd determining module is used for：Respectively
The facial characteristics of each object in the perpetual object and the matching facial characteristics of each corresponding objects are determined described one
The position of the record mask in two field picture and the follow-up two field picture and original dimension；Selected from each original dimension determined
One of size is used as reference dimension；And adjust the original dimension in a two field picture and the follow-up two field picture
Into the reference dimension.
For above-mentioned video recording device, in a kind of possible implementation, the reference dimension is regarded according to
The resolution ratio of each two field picture of frequency and pre-set.
For above-mentioned video recording device, in a kind of possible implementation, the record screen unit includes：Loading mould
Block, for default expression to be loaded into the record mask；And record panel module, it is connected with the load-on module, for root
The position of the record mask according to the expression for being loaded and in each two field picture and size are recorded to the video.
For above-mentioned video recording device, in a kind of possible implementation, the facial characteristics recognition unit is used for：
Facial critical zone locations in each two field picture of the video played are positioned, wherein, the critical zone locations
Including at least one of eyebrow, eyes, nose, face, ear and face mask region.
According to the video recording method and device of the embodiment of the present disclosure, record screen is applied to by by facial characteristics identification technology
Technology, position and size thus, it is possible to flexibly set record mask, so as to record out the desired video of user, improves user's body
Test.
According to below with reference to the accompanying drawings to detailed description of illustrative embodiments, the further feature and aspect of the disclosure will become
It is clear.
Brief description of the drawings
Comprising in the description and the part that constitutes specification accompanying drawing together illustrated with specification it is of the invention
Exemplary embodiment, feature and aspect, and for explaining principle of the invention.
Fig. 1 shows the flow chart of the video recording method according to the embodiment of the disclosure one；
Fig. 2 shows to detect the schematic diagram of positive face；
Fig. 3 shows to detect the schematic diagram of side face；
Fig. 4 shows the schematic diagram of the size for determining the record mask of positive face；
Fig. 5 shows the schematic diagram of the size for determining the facial record mask of side；
Fig. 6 shows the flow chart of the video recording method of another embodiment of the present disclosure；
Fig. 7 shows the flow chart of the video recording method of the another embodiment of the disclosure；
Fig. 8 shows the face tracking identification of the embodiment of the disclosure one and follows the trail of the schematic diagram of recorded video；
Fig. 9 shows the structured flowchart of the video recording device according to the embodiment of the disclosure one；
Figure 10 shows the structured flowchart of the video recording device according to another embodiment of the present disclosure；And
Figure 11 is the structured flowchart of the video recording device according to an exemplary embodiment.
Specific embodiment
Describe various exemplary embodiments, feature and the aspect of the disclosure in detail below with reference to accompanying drawing.It is identical in accompanying drawing
Reference represent the same or analogous element of function.Although the various aspects of embodiment are shown in the drawings, remove
Non-specifically is pointed out, it is not necessary to accompanying drawing drawn to scale.
Special word " exemplary " means " being used as example, embodiment or illustrative " herein.Here as " exemplary "
Illustrated any embodiment should not necessarily be construed as preferred or advantageous over other embodiments.
In addition, in order to better illustrate the disclosure, numerous details are given in specific embodiment below.
It will be appreciated by those skilled in the art that without some details, the disclosure can equally be implemented.In some instances, for
Method well known to those skilled in the art, means, element and circuit are not described in detail, in order to highlight the purport of the disclosure.
Embodiment 1
Fig. 1 shows the flow chart of the video recording method according to the embodiment of the disclosure one.As shown in figure 1, the method can be with
Comprise the following steps：
Step S100, each two field picture of video to being played carry out facial characteristics identification frame by frame；
Step S110, according to facial characteristics recognition result come determine in each two field picture record mask position and size；
And
Step S120, the position according to the record mask in each two field picture and size are recorded to video.
Specifically, first, the video that carry out recording screen is played in video player, record screen software is then for example clicked on
Button, thus ejection record screen sets frame, and clicks on specific button inframe is set (for example face records button).Wherein, broadcast
The video put can be the Online Video that is got from internet, or have stored in local storage, for example hard
Local video on disk.
For above-mentioned steps S110, for each two field picture of the video played, facial characteristics can be frame by frame carried out to it
Identification, to detect in each two field picture with the presence or absence of face (face).And in the case where there is face, further determine that the face
Particular location and the facial profile size of the portion in two field picture.
In a kind of possible implementation, can be to the facial key area in each two field picture of the video played
Position is positioned, and carries out feature recognition to each critical zone locations, to obtain the facial facial characteristics.Wherein, should
Critical zone locations include at least one of eyebrow, eyes, nose, face, ear and face mask region, the face
Feature can include position and its profile size of the face in two field picture.It should be noted that the critical zone locations are not
It is limited to example listed above, as long as and the position of facial characteristics can be reflected.Additionally, detected face can be with
It is front (as shown in Figure 2), or side (as shown in Figure 3), and a certain degree of blocking and polygonal can be supported
Degree detection.
In a kind of possible implementation, in a two field picture, it is understood that there may be the face of multiple objects (such as personage).
If there is multiple faces, then pair it is identified with the critical zone locations of each face respectively, it is special with the face for obtaining each face
Levy.
In a kind of possible implementation, after identifying face and obtaining its facial characteristics, can be by these
Information is stored in memory as facial characteristics recognition result.
For above-mentioned steps S110, by carrying out the face that facial characteristics is recognized and obtains each two field picture to each two field picture
After feature recognition result, record screen when can be determined to carry out each two field picture record screen according to resulting facial characteristics result
The position of frame and size.
If for example, detect a face in a certain two field picture, and having obtained its facial characteristics (including face
Position and profile size in two field picture), then can be determined to record position and the size of mask according to the facial characteristics.Its
In, the record mask is at least capable of the region (as shown in Figure 4,5) of the whole face of frame choosing.And for example, if detected in a certain two field picture
To multiple faces, then determined to record position and the size of mask according to the plurality of facial facial characteristics.Wherein, the record mask is extremely
It is capable of regions of whole this multiple face of frame choosing less.And for example, if being not detected by face in a certain two field picture, i.e. the frame figure
In the absence of face as in, then can make record mask temporary extinction, i.e., the two field picture not recorded, when in follow-up two field picture
In when detecting face again, then there is record mask, and determine its positions and dimensions.
For above-mentioned steps S120, the position of record mask when record screen is carried out to each two field picture is determined in step s 110
Put and during size, for example, can click on beginning video record button, with the position according to the record mask determined and size pair
The video is recorded.Thus, the video clip of the facial expression including various faces is produced.
After recording terminates, for example, the video of recording can be preserved into general mp4 forms automatically, and preserve to for example
A certain file on local hard drive.When user needs to watch the video of the recording, enter by the file for clicking on the mp4 forms
Row viewing.
According to the video recording method of the embodiment of the present disclosure, can be entered by the facial characteristics of each two field picture in video
Row identification simultaneously determines position and the size of the record mask in each two field picture, then basis according to facial characteristics recognition result
The position of the record mask determined and size are recorded to video.So, can be answered by by facial characteristics identification technology
Use in record screen technology, position and the size of mask are recorded thus, it is possible to flexibly set, so that the desired video of user is recorded out,
Improve Consumer's Experience.
Embodiment 2
In the record screen of above-described embodiment, due to may not for the facial profile size detected by each two field picture
Together, the size therefore for the record mask of each two field picture is likely to difference.Using different record mask sizes come to each frame figure
As when being recorded, the size of resulting each two field picture is different.When so each two field picture is spliced into video, may produce
Discontinuous, the unnatural phenomenon of video image.
In order to solve the above problems, in the present embodiment, using by the record mask size adjusting of each two field picture into identical chi
Video is recorded again after very little.
Fig. 6 shows the flow chart of the video recording method of another embodiment of the present disclosure.Label and Fig. 1 identicals in Fig. 6
Step has identical function, for simplicity, omits the detailed description to these steps.
As shown in fig. 6, the video recording method of the present embodiment exists with the main distinction of the video recording method shown in Fig. 1
In above-mentioned steps S110 may comprise steps of：
Step S210, according to facial characteristics recognition result come determine in each two field picture record mask position and initial chi
It is very little；
Step S220, from each original dimension determined one of size is selected as reference dimension；And
Step S230, the original dimension in a two field picture and follow-up two field picture is adjusted to the reference dimension.
Specifically, after obtaining identified facial characteristics recognition result in the step s 100, can basis first
The facial characteristics recognition result come determine for each two field picture record mask position and record mask original dimension.Wherein,
These original dimensions may be by the facial characteristics recognition result that is identified it is different and different.Then, from identified each
In original dimension, one of them appropriate size is selected as reference dimension, then by the size of the record mask in each two field picture
It is adjusted to the reference dimension.Wherein, in a kind of possible implementation, the reference dimension is each frame figure according to video
The resolution ratio of picture and pre-set.Also, if the original dimension determined is more than the reference dimension, then for example can be by
The two field picture is scaled so that get profit with the record mask with the reference dimension carry out during video record can frame choose
Facial zone in the two field picture.
In a kind of possible implementation, the reference dimension is the full-size in each original dimension determined.
Certainly, the reference dimension not limited to this, and can be any appropriate size, as long as the two field picture recorded out using the size
Resolution ratio disclosure satisfy that the definition of user's viewing.
Then, in follow-up step S120, position and adjustment using the record mask of each two field picture for determining before
The size of record mask afterwards carries out video record.So, the size of the two field picture recorded out for each two field picture is consistent
, it is discontinuous, unnatural therefore, it is possible to solve the problems, such as the video image when these two field pictures are spliced.
It should be noted that solve the problems, such as that discontinuous, the unnatural method of video image is not limited to above-described embodiment,
Other methods can be used.For example, can be first according to the facial characteristics recognition result identified in step S100 to each frame
Image is recorded, then, on the basis of the size of the two field picture of the appropriate size (such as full-size) recorded out, by it
The size of its two field picture is adjusted to the appropriate size.Wherein, for by the size adjusting of other two field pictures into the appropriate size
Method can be edge filling background etc. in these other two field pictures.Make the chi of other two field pictures by filling background
It is very little become appropriate size after, then these two field pictures are spliced, so equally can solve the problem that by the splicing of these two field pictures
When discontinuous, the unnatural problem of video image.
So, according to the video recording method of the embodiment of the present disclosure, can be applied to by by facial characteristics identification technology
In record screen technology, position and size thus, it is possible to flexibly set record mask, so as to record out the desired video of user, are improved
Consumer's Experience.Also, the size of the record mask that the present embodiment can be determined by adjustment based on facial characteristics identification technology,
So that discontinuous, the unnatural problem of video image will not be produced when video image splices.
Embodiment 3
As described above, in a two field picture, the face of multiple objects can be can recognize that.In this case, user may
Only it is expected for the face of wherein some or multiple object to be recorded, i.e., when being recorded to the video, only recording should
The face of one object or the plurality of object, thus realize the facial expression to an object or the plurality of object record and
Follow the trail of.
Therefore, above-mentioned purpose can be realized using the flow chart of the video recording method shown in Fig. 7 of the present embodiment.
Fig. 7 shows the flow chart of the video recording method of the another embodiment of the disclosure.Label and Fig. 1 identicals in Fig. 7
Step has identical function, for simplicity, omits the detailed description to these steps.
As shown in fig. 7, the video recording method of the present embodiment exists with the main distinction of the video recording method shown in Fig. 1
In above-mentioned steps S110 may comprise steps of：
Step S310, in the case of the facial characteristics that multiple objects are identified from a two field picture of video first, from
At least one object is selected in multiple objects as perpetual object；
Step S320, in the follow-up two field picture of a two field picture, frame by frame determine with perpetual object in each object face
The matching facial characteristics of the similarity of feature corresponding objects respectively below predetermined similarity threshold；And
The matching face of step S330, the facial characteristics of each object respectively in perpetual object and each corresponding objects is special
Levy the position to determine the record mask in a two field picture and follow-up two field picture and size.
First, for object record and the situation of tracking is illustrated.
Specifically, in above-mentioned steps S310, when facial characteristics identification is carried out to each two field picture frame by frame, if at certain
The face of multiple objects is identified in one two field picture, then user's object interested can be selected to make from the plurality of object
It is perpetual object, and stores the facial characteristics of the perpetual object in memory.Also, in above-mentioned steps S330, according to
The facial characteristics of the perpetual object can determine position and the size of the record mask of the two field picture.
Then, in the facial characteristics identification to follow-up two field picture, using the perpetual object as record screen object of focus, so that
Follow the trail of a series of facial expressions change of the perpetual object.Specifically, in above-mentioned steps S320, then to the two field picture
The facial characteristics of follow-up two field picture is identified, and determines to whether there is the perpetual object in these follow-up two field pictures.For example,
In a certain successive image, identify multiple objects, then by the facial characteristics of this multiple object respectively with the concern for setting before
The facial characteristics of object compares, to determine the similarity of these facial characteristics and the facial characteristics of perpetual object.If a certain
Difference between the characteristic value of the facial characteristics of the characteristic value of the facial characteristics of object and the perpetual object for setting before is small, i.e., it
Between similarity be less than default similarity threshold (in other words, the similarity of the two objects is high), then it represents that this pair
As object, the i.e. object to be followed the trail of for user is the perpetual object in the two field picture.Here, by the facial characteristics of the object
Referred to as match facial characteristics.In addition, if do not exist the perpetual object in a certain follow-up two field picture, then can not be to the two field picture
Recorded.
Successively to video in all follow-up two field picture perform the treatment of above-mentioned steps S320.
So, can confirm that in follow-up two field picture with the presence or absence of the perpetual object.Also, in the feelings that there is the perpetual object
Under condition, in above-mentioned steps S330, facial characteristics (matching facial characteristics) according to the perpetual object determines its corresponding frame
The position of the record mask of image and size.
Equally, user identify first a certain two field picture have multiple objects it is facial when, user can also be therefrom
Two or more objects are selected as perpetual object, with respectively to perpetual object in each object recorded and followed the trail of.
For example, the object 1 and object 2 in the multiple objects of selection are used as perpetual object 1 and perpetual object 2.And in storage
The facial characteristics of the perpetual object 1 and perpetual object 2 is stored in device.Also, in above-mentioned steps S330, according to the perpetual object
1 and the facial characteristics record screen that can determine respectively in the two field picture for perpetual object 1 and perpetual object 2 of perpetual object 2
The position of frame and size.
Then, in the facial characteristics identification to follow-up two field picture, respectively using the perpetual object 1 and perpetual object 2 as
Record screen object of focus, so as to follow the trail of a series of facial expressions change of perpetual object 1 and perpetual object 2.Specifically, above-mentioned
In step S320, then the facial characteristics to the follow-up two field picture of the two field picture is identified, and determines these follow-up two field pictures
In whether there is the perpetual object 1 and perpetual object 2.For example, in a certain successive image, identifying multiple objects, then will
The facial characteristics of this multiple object respectively compared with the perpetual object 1 and the facial characteristics of perpetual object 2 that set before, with point
Do not determine these facial characteristics with perpetual object 1 and the similarity of the facial characteristics of perpetual object 2.If the face of a certain object
Difference between the characteristic value of the facial characteristics of the characteristic value of feature and the perpetual object 1 for setting before is small, i.e., between them
Similarity is less than default similarity threshold (in other words, the similarity of the two objects is high), then it represents that the object is user
Object, the i.e. object to be followed the trail of is the perpetual object 1 in the two field picture.Similarly, if the facial characteristics of a certain object
Difference between the characteristic value of the facial characteristics of characteristic value and the perpetual object 2 for setting before is small, i.e., the similarity between them
Less than default similarity threshold (in other words, the similarity of the two objects is high), then it represents that the object to be chased after for user
The object of track, the i.e. object are the perpetual object 2 in the two field picture.Here, the facial characteristics of a certain object is referred to as matching
Facial characteristics.In a kind of possible implementation, perpetual object 1 may be only existed in follow-up two field picture, it is also possible to only exist
Perpetual object 2, it is also possible to while there is perpetual object 1 and perpetual object 2.
In addition, if do not exist perpetual object 1 and perpetual object 2 in a certain follow-up two field picture, then can not be to the frame figure
As being recorded.
Successively to video in all follow-up two field picture perform the treatment of above-mentioned steps S320.
Then, in step S330, for follow-up two field picture in each perpetual object 1 and perpetual object 2, respectively according to it
Facial characteristics is matched to determine position and the size of the record mask in follow-up two field picture.
Record and the tracking of object interested in user are described to select two perpetual objects as example above, but
It is that those skilled in the art are able to know that, the record of object interested in user and the equally applicable choosing of the said process of tracking
Select more objects.
It should be noted that if selected for multiple objects, then the position of record mask can be determined for each object respectively
And size, each object is recorded respectively then, recorded and followed the trail of with the facial expression change respectively to each object.This
Outward, can also by this multiple object box choose one record mask in, this multiple object is recorded as an entirety
And tracking, can so reflect the scene corresponding to facial expression.
So, in the present embodiment, it may not be necessary to which the face of all objects to being identified is recorded, and is only recorded
User expects the object recorded, so as to realize the record to a series of expression shape changes of the object and tracking.
In a kind of possible implementation, it may not be necessary to selected when the facial characteristics of multiple objects is first identified
Perpetual object, and can when user sees object interested again by the Object Selection be perpetual object.
In a kind of possible implementation, in same two field picture, it is understood that there may be the facial characteristics of multiple faces and pass
The similarity for noting the facial characteristics of object is respectively less than the situation of default similarity threshold.For example, the front and side of same personage
Face.In such a case, it is possible to select the facial corresponding object of (gap value is smaller) higher with similarity right as paying close attention to
As, for example select the personage corresponding with front as perpetual object.
In a kind of possible implementation, if in the identification of follow-up two field picture, once find to exist do not have
The two field picture of above-mentioned matching facial characteristics, then can no longer carry out feature recognition to follow-up two field picture, and respectively according to at present
Untill perpetual object facial characteristics come determine these two field pictures record mask position and size.
For example, there are 100 two field pictures in video, perpetual object is determined in 1 two field picture, after then recognizing successively
Continuous the 2nd two field picture, the 3rd two field picture ..., found during in the absence of the perpetual object, then not when in such as 20 two field picture
Feature recognition is carried out to follow-up two field picture again, but merely with the face of the perpetual object in the 1st two field picture~the 19th two field picture
Feature determines position and the size of the record mask of the 1st two field picture~the 19th two field picture respectively, and according to the record determined
The position of mask and size are recorded to the 1st two field picture~the 19th two field picture respectively, and no longer record follow-up two field picture.This
Sample, can only record the two field picture in one section of continuous video, so as to obtain the consecutive variations of facial expression.
Above is using an object as perpetual object as example is described, but disclosure not limited to this, with multiple
Object is equally applicable to said process as the situation of perpetual object.
In a kind of possible implementation, user can stop the record of video at any two field picture according to their needs
System.For example, face is provided with player records stop button, user is pressed after face recording stop button, you can stopped
Only face is recorded.
Additionally, when position and the size of record mask are determined in above-mentioned steps S330, being equally applicable above-mentioned steps
S210~S230, to solve the problems, such as the discontinuous, unnatural of video image after video record.
Specifically, above-mentioned steps S330 specifically may comprise steps of：Each object in perpetual object respectively
Facial characteristics and the matching facial characteristics of each corresponding objects determine the record mask in the two field picture and follow-up two field picture
Position and original dimension；One of size is selected from each original dimension determined as reference dimension；And will be
Original dimension in one two field picture and follow-up two field picture is adjusted to the reference dimension.
Additionally, in a kind of possible implementation, during video record, can also be to the face that is recognized in video
Portion carries out the operation such as entertaining editor.For example, in the case of the face for detecting multiple objects, if there is user to be not desired in video
See face, then can carry out entertaining modification to face, such as put on mask to face or addition of expressing one's feelings is carried out to face, in table
After feelings addition is completed, for example, save button can be clicked on, be preserved with to the expression added.
Now, during the expression of addition may apply to whole two field pictures of video, it is also possible to which being applied to that user is desired should
In the two field picture used.
Additionally, in a kind of possible implementation, in any of the above-described embodiment, above-mentioned steps S120 can include with
Lower step：Default expression is loaded into record mask；And the record mask according to the expression for being loaded and in each two field picture
Position and size video recorded.
For example, expression addition button can set, an expression comprising multiple expressions occurs after clicking on
Bag, then therefrom selects an expression to be loaded into record mask.Then, in video record, you can according to the expression for being loaded
And record mask in each two field picture position and size video is recorded.
In a kind of possible implementation, loading can be preset in the whole two field pictures that have identified face of video
Expression, it is also possible to default expression is loaded in the two field picture of part.In addition, being directed to each two field picture, the default expression for being loaded
Can be with identical, it is also possible to different.
So, by loading default expression during video record, the interest in video record can be increased.
So, according to the video recording method of the embodiment of the present disclosure, can be applied to by by facial characteristics identification technology
In record screen technology, position and size thus, it is possible to flexibly set record mask, so as to record out the desired video of user, are improved
Consumer's Experience.Also, the size of the record mask that the present embodiment can be determined by adjustment based on facial characteristics identification technology,
So that discontinuous, the unnatural problem of video image will not be produced when video image splices.Additionally, the present embodiment can be with
By setting perpetual object in a certain two field picture, and cause to follow the trail of the perpetual object in follow-up two field picture, then according to pass
The facial characteristics of object is noted to determine position and the size of the record mask of each two field picture, it is interested in user thus, it is possible to realize
The record of perpetual object and tracking.Additionally, the present embodiment can load default expression during video record, thus increase
The interest of video record.
Embodiment 4
Concrete application scene and corresponding practical operation step and device present embodiment illustrates the disclosure etc..
First, user carry out video record general operation step it is as follows：
(1) after user clicks on and plays video, record screen software push buttons are clicked on, system ejection record screen sets frame, sets inframe
Click on " face is recorded " button；
(2) record mask can give tacit consent to frame and choose the facial positions identified in video, if occurring more than two on video pictures
During facial more than individual, record mask can only give tacit consent to frame and select a face, the face to be recorded also dependent on oneself of user to be adjusted
It is whole, mask will be recorded and moved on the face for needing to record, record mask can be repositioned according to face key point feedback data
(critical zone locations of face in positioning video)；
(3) after the choosing of facial frame determines, you can click on " starting to record " button；
(4) in recording process, record mask can be recorded as the positive face of face and side face move tracking, when face is removed
After record mask, video record is to terminate, additionally, user also can in advance terminate recording process；
(5) after the completion of face action in video, record mask can be disappeared automatically, and complete rear recording process is preserved automatically；
(6) after recording terminates, the video of recording automatic can be preserved into general mp4 forms by system, and be preserved to this
In ground file.To checking in local folders when user needs to play the video recorded.
On the basis of above-mentioned steps, user can also carry out the operations such as a certain degree of interesting editor.
For example, in recording process, the operation such as entertaining editor can be carried out to the face (face) recognized in video, such as
The face that fruit does not want to see that in video memory in user, then can carry out entertaining modification to the face, such as put on mask to face
Or expression addition etc. is carried out to face, and after the completion of addition, " preservation " button is clicked on, preserved with to expression addition.Now
The expression of addition, may apply in whole collection video, as long as this face occurs in video, all can be with mask or expression etc..
Can so reduce scheme of the user to personage, and reduce the demand of F.F., increased interest when user sees video etc..
Additionally, above-mentioned steps can be realized using following face tracking device and record screen device.
Wherein, the face tracking device can include：
(1) calling module, feature (facial characteristics) comparator；
(2) relation sets up module, for according to each face (face) in video sequence frame (each two field picture in video)
Face feature information, the corresponding relation between the ID values of the characteristic value people corresponding with face for setting up different faces so that this
A little characteristic values are compared in feature comparator；
(3) searching modul, for the comparing according to feature comparator, searches the people minimum with record screen object of focus gap value
The facial characteristics of face；
(4) memory module, for the face characteristic for exporting (identification) to be stored；
(5) face tracking module, the face minimum with record screen object of focus gap value for following the trail of video sequence frame in；
(6) identification module, for when there is two or more face simultaneously in video, taking the minimum face conduct of gap value
Record screen object of focus；
(7) recognition memory, the face that video sequence frame in is recognized is stored.
Additionally, the record screen device can include：
(1) monitoring modular, the signal that signal and face tracking device for monitoring record screen triggering send, starts to record；
(2) collection module, the frame of video for face tracking to be recorded is collected
(3) data memory module, for the video requency frame data of recording to be stored.
Fig. 8 shows the face tracking identification of the embodiment of the disclosure one and follows the trail of the schematic diagram of recorded video, and detailed process is detailed
See description below.
(1) in the video played, face (face) number and the face location in each two field picture of video are detected frame by frame
Information (" Face datection " in corresponding diagram 8).
(2) model of the analysis with face characteristic, probability match (facial characteristics identification) is carried out with face characteristic model.
Specifically, using face (face) critical point detection method, the face feature based on people judges whether people
Face.The critical zone locations of face in positioning video, including eyebrow, eyes, nose, face, face mask etc..The detection method
Support is blocked and multi-orientation Face to a certain degree.By using face critical point detection technology, face can be accurately positioned (such as
The front of the face shown in Fig. 2 and the side of face as shown in Figure 3) (" face critical point detection " in corresponding diagram 8).
(3) face is chosen, and the face is set as record screen object of focus.After setting successfully, backstage can record institute
The crucial point feature of face is chosen, and is stored in face comparator.The face is the prime focus of follow-up tracking.
Then, the multiple faces that will occur in video pictures carry out positional information memory, and the feature using each face is remembered
Recall the characteristic value needed for obtaining.During carrying out face tracking, it is necessary to by the characteristic value of currently detected face with before
The character pair value of the face as record screen object of focus stored in feature comparator is compared, to check gap
Value.If currently detected face with stored before as the human face similarity degree for comparing be less than default gap value (phase
Like degree threshold value) (i.e. similarity is high), then the face is defined as the face to be followed the trail of.If on video pictures occur two and
More than face with stored before as the human face similarity degree for comparing be less than default gap value, then by similarity gap value
Minimum face is defined as the face to be followed the trail of.Also, the crucial point feature of the face is preserved (in corresponding diagram 8
" face comparator ", " face characteristic extraction ", " recognition of face " and " storage ").
(4) it is then determined recording the positional information of mask choosing, the Critical point model according to face carries out the diagonal of outermost edge
Connection, determines position and the size (as shown in Figure 4,5) (" record mask positioning " in corresponding diagram 8) of record mask.
(5) record mask is shown on video pictures, what is fed back in record mask position according in face tracking identification process
Crucial point feature, recording is tracked to video.After key point (the front, side) feature followed the trail of disappears, terminate to record, its
In, it is also possible to need extract operation (" focusing of record mask position " in corresponding diagram 8, " the record screen for terminating to record according to user
Frame is followed the trail of " and " recorded video ").
(6) video that will be recorded out carries out video encapsulation, is then stored in the (" video in corresponding diagram 8 in local folders
Encapsulation " and " preserving local ").
Additionally, as the operation of addition expression etc. during video record, relating generally to such as lower module：
(1) identification module, the human face expression for recognizing frame of video generates recognition result；
(2) acquisition module, for obtaining default expression, and selects one of them to carry out textures synthesis；
(3) determine that mould is fast, for determining expression loading position in the video frame；
(4) sending module, the loading figure for sending expression special efficacy；
(5) load-on module, the loading of the loading figure for carrying out expression special efficacy in such as each frame of video；
(6) display module, in video playback, showing expression figure in the face in such as each frame of video；
Wherein it is possible to an expression in default expression bag is selected, while match cognization is carried out to the face in frame of video,
Generation recognition result, also, determine loading position of the expression to be loaded in instant frame of video.Additionally, by each video
The parameter point of the face characteristic in frame is synthesized with expression.Then, in video record, each frame of video to being loaded with expression
Recorded.So, interest during user's viewing video can be increased.
So, according to the video recording method and related device of the embodiment of the present disclosure, can be recognized by by facial characteristics
Technology is applied in record screen technology, position and size thus, it is possible to flexibly set record mask, so as to record out desired by user
Video, improve Consumer's Experience.Also, the present embodiment can be by setting record screen object of focus (concern in a certain two field picture
Object), and cause the record screen object of focus is followed the trail of in follow-up two field picture, then according to record screen object of focus facial characteristics come
Position and the size of the record mask of each two field picture are determined, thus, it is possible to realizing the record of perpetual object interested in user and chasing after
Track.Additionally, the present embodiment can load default expression during video record, thus increase the interest of video record.
Embodiment 5
Fig. 9 shows the structured flowchart of the video recording device according to the embodiment of the disclosure one.As shown in figure 9, the video is recorded
Device processed 90 can include：Facial characteristics recognition unit 91, each two field picture for the video to being played carries out face frame by frame
Feature recognition；Determining unit 92, is connected with the facial characteristics recognition unit 91, for according to facial characteristics recognition result come really
The position of the record mask being scheduled in each two field picture and size；And record screen unit 93, it is connected with the determining unit 92, use
The video is recorded in the position according to the record mask in each two field picture and size.
In a kind of possible implementation, the determining unit 92 includes：First determining module 921, for according to face
Portion's feature recognition result come determine in each two field picture record mask position and original dimension；First choice module 922,
It is connected with first determining module 921, for selecting one of size from each original dimension determined as base
Object staff cun；And adjusting module 923, it is connected with the first choice module 922, for by the record screen in each two field picture
The original dimension of frame is adjusted to the reference dimension.
In a kind of possible implementation, the reference dimension be the resolution ratio of each two field picture according to the video and
Pre-set.
In a kind of possible implementation, the record screen unit 93 can include：Load-on module 931, for that will preset
Expression be loaded into it is described record mask in；And record panel module 932, it is connected with the load-on module 931, for according to being loaded
Expression and record mask in each two field picture position and size the video is recorded.
In a kind of possible implementation, the facial characteristics recognition unit 91 specifically for：To the video played
Each two field picture in facial critical zone locations positioned, wherein, the critical zone locations include eyebrow, eyes,
At least one of nose, face, ear and face mask region.
The video recording device of the embodiment of the present disclosure can be used to realize in above-described embodiment 1~4 described in any embodiment
Video recording method.The idiographic flow of the video recording method described in above-described embodiment 1~4 is see above-described embodiment 1~4
Elaborate.
So, according to the video recording device of the embodiment of the present disclosure, can be applied to by by facial characteristics identification technology
In record screen technology, position and size thus, it is possible to flexibly set record mask, so as to record out the desired video of user, are improved
Consumer's Experience.Also, the size of the record mask that the present embodiment can be determined by adjustment based on facial characteristics identification technology,
So that discontinuous, the unnatural problem of video image will not be produced when video image splices.Additionally, the present embodiment can be with
Default expression is loaded during video record, thus increases the interest of video record.
Embodiment 6
Figure 10 shows the structured flowchart of the video recording device according to another embodiment of the present disclosure.Label and figure in Figure 10
9 identical components have identical function, for simplicity, omit the detailed description to these components.
As shown in Figure 10, the main region of the video recording device 90 shown in the video recording device 100 of the present embodiment and Fig. 9
It is not that the determining unit 92 can also include：Second selecting module 1001, for first from a frame figure of the video
In the case of the facial characteristics of multiple objects is identified as in, at least one object is selected from the multiple object as concern
Object；Second determining module 1002, is connected with second selecting module 1001, with for the subsequent frame in a two field picture
In image, determine the similarity with the facial characteristics of each object in the perpetual object respectively in predetermined similarity threshold frame by frame
The matching facial characteristics of the following corresponding objects of value；And the 3rd determining module 1003, connect with second determining module 1002
Connect, the matching facial characteristics of facial characteristics and each corresponding objects for each object respectively in the perpetual object, come
It is determined that the position for recording mask and size in a two field picture and the follow-up two field picture.
In a kind of possible implementation, the 3rd determining module 1003 is additionally operable to：In the rear in continuous two field picture,
If there is the two field picture without the matching facial characteristics, the then face of each object respectively in the perpetual object
The matching facial characteristics of feature and each corresponding objects determines from the two field picture to without the matching facial characteristics
The position of the record mask in the two field picture between two field picture and size.
In a kind of possible implementation, the 3rd determining module 1003 can be specifically for：Respectively according to described
The facial characteristics of each object in perpetual object and the matching facial characteristics of each corresponding objects to determine in a two field picture and
The position of the record mask in the follow-up two field picture and original dimension；One of them is selected from each original dimension determined
Size is used as reference dimension；And the original dimension in a two field picture and the follow-up two field picture is adjusted to the base
Object staff cun.
In a kind of possible implementation, the reference dimension be the resolution ratio of each two field picture according to the video and
Pre-set.
The video recording device of the embodiment of the present disclosure can be used to realize in above-described embodiment 1~4 described in any embodiment
Video recording method.The idiographic flow of the video recording method described in above-described embodiment 1~4 is see above-described embodiment 1~4
Elaborate.
So, according to the video recording device of the embodiment of the present disclosure, can be applied to by by facial characteristics identification technology
In record screen technology, position and size thus, it is possible to flexibly set record mask, so as to record out the desired video of user, are improved
Consumer's Experience.Also, the size of the record mask that the present embodiment can be determined by adjustment based on facial characteristics identification technology,
So that discontinuous, the unnatural problem of video image will not be produced when video image splices.Additionally, the present embodiment can be with
By setting perpetual object in a certain two field picture, and cause to follow the trail of the perpetual object in follow-up two field picture, then according to pass
The facial characteristics of object is noted to determine position and the size of the record mask of each two field picture, it is interested in user thus, it is possible to realize
The record of perpetual object and tracking.Additionally, the present embodiment can load default expression during video record, thus increase
The interest of video record.
Embodiment 7
Figure 11 is the structured flowchart of the video recording device according to an exemplary embodiment.Wherein the device 800 is used
In the video recording method described in execution above-described embodiment.For example, device 800 can be mobile phone, computer, numeral is wide
Broadcast terminal, messaging devices, game console, tablet device, Medical Devices, body-building equipment, personal digital assistant etc..
Reference picture 11, device 800 can include following one or more assemblies：Processing assembly 802, memory 804, power supply
Component 806, multimedia groupware 808, audio-frequency assembly 810, the interface 812 of input/output (I/O), sensor cluster 814, and
Communication component 816.
The integrated operation of the usual control device 800 of processing assembly 802, such as with display, call, data communication, phase
Machine is operated and the associated operation of record operation.Processing assembly 802 can refer to including one or more processors 820 to perform
Order, to complete all or part of step of above-mentioned method.Additionally, processing assembly 802 can include one or more modules, just
Interaction between processing assembly 802 and other assemblies.For example, processing assembly 802 can include multi-media module, it is many to facilitate
Interaction between media component 808 and processing assembly 802.
Memory 804 is configured as storing various types of data supporting the operation in device 800.These data are shown
Example includes the instruction for any application program or method operated on device 800, and contact data, telephone book data disappears
Breath, picture, video etc..Memory 804 can be by any kind of volatibility or non-volatile memory device or their group
Close and realize, such as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM) is erasable to compile
Journey read-only storage (EPROM), programmable read only memory (PROM), read-only storage (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 806 provides electric power for the various assemblies of device 800.Power supply module 806 can include power management system
System, one or more power supplys, and other generate, manage and distribute the component that electric power is associated with for device 800.
Multimedia groupware 808 is included in one screen of output interface of offer between described device 800 and user.One
In a little embodiments, screen can include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch-screen, to receive the input signal from user.Touch panel includes one or more touch sensings
Device is with the gesture on sensing touch, slip and touch panel.The touch sensor can not only sensing touch or sliding action
Border, but also detection and the touch or slide related duration and pressure.In certain embodiments, many matchmakers
Body component 808 includes a front camera and/or rear camera.When device 800 be in operator scheme, such as screening-mode or
During video mode, front camera and/or rear camera can receive outside multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or with focusing and optical zoom capabilities.
Audio-frequency assembly 810 is configured as output and/or input audio signal.For example, audio-frequency assembly 810 includes a Mike
Wind (MIC), when device 800 is in operator scheme, such as call model, logging mode and speech recognition mode, microphone is matched somebody with somebody
It is set to reception external audio signal.The audio signal for being received can be further stored in memory 804 or via communication set
Part 816 sends.In certain embodiments, audio-frequency assembly 810 also includes a loudspeaker, for exports audio signal.
, to provide interface between processing assembly 802 and peripheral interface module, above-mentioned peripheral interface module can for I/O interfaces 812
To be keyboard, click wheel, button etc..These buttons may include but be not limited to：Home button, volume button, start button and lock
Determine button.
Sensor cluster 814 includes one or more sensors, and the state for providing various aspects for device 800 is commented
Estimate.For example, sensor cluster 814 can detect the opening/closed mode of device 800, the relative positioning of component is for example described
Component is the display and keypad of device 800, and sensor cluster 814 can be with 800 1 components of detection means 800 or device
Position change, user is presence or absence of with what device 800 was contacted, the orientation of device 800 or acceleration/deceleration and device 800
Temperature change.Sensor cluster 814 can include proximity transducer, be configured to be detected when without any physical contact
The presence of neighbouring object.Sensor cluster 814 can also include optical sensor, such as CMOS or ccd image sensor, for into
As being used in application.In certain embodiments, the sensor cluster 814 can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between device 800 and other equipment.Device
800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G, or combinations thereof.In an exemplary implementation
In example, communication component 816 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 816 also includes near-field communication (NFC) module, to promote junction service.Example
Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 800 can be by one or more application specific integrated circuits (ASIC), numeral letter
Number processor (DSP), digital signal processing appts (DSPD), PLD (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components realization, for performing the above method.
In the exemplary embodiment, a kind of non-volatile computer readable storage medium storing program for executing including instructing, example are additionally provided
Such as include the memory 804 of instruction, above-mentioned instruction can be performed to complete the above method by the processor 820 of device 800.
The present invention can be system, method and/or computer program product.Computer program product can include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the invention.
Computer-readable recording medium can be the tangible of the instruction that holding and storage are used by instruction execution equipment
Equipment.Computer-readable recording medium for example can be-- but be not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electromagnetism storage device, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer-readable recording medium
More specifically example (non exhaustive list) includes：Portable computer diskette, hard disk, random access memory (RAM), read-only deposit
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static RAM (SRAM), portable
Compact disk read-only storage (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
Be stored with instruction punch card or groove internal projection structure and above-mentioned any appropriate combination.Calculating used herein above
Machine readable storage medium storing program for executing is not construed as instantaneous signal in itself, the electromagnetic wave of such as radio wave or other Free propagations, logical
Cross electromagnetic wave (for example, the light pulse for passing through fiber optic cables) that waveguide or other transmission mediums propagate or by wire transfer
Electric signal.
Computer-readable program instructions as described herein can from computer-readable recording medium download to each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, LAN, wide area network and/or wireless network
Portion's storage device.Network can include copper transmission cable, Optical Fiber Transmission, be wirelessly transferred, router, fire wall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for storing the meter in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
For perform the present invention operation computer program instructions can be assembly instruction, instruction set architecture (ISA) instruction,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming language
Source code or object code that any combination is write, programming language of the programming language including object-oriented-such as
Smalltalk, C++ etc., and routine procedural programming languages-such as " C " language or similar programming language.Computer
Readable program instructions can perform fully on the user computer, partly perform on the user computer, as one solely
Vertical software kit is performed, part performs or completely in remote computer on the remote computer on the user computer for part
Or performed on server.In the situation for being related to remote computer, remote computer can be by the network-bag of any kind
LAN (LAN) or wide area network (WAN)-be connected to subscriber computer are included, or, it may be connected to outer computer (such as profit
With ISP come by Internet connection).In certain embodiments, by using computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as PLD, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can perform computer-readable program instructions, so as to realize each side of the invention
Face.
Referring herein to method according to embodiments of the present invention, device (system) and computer program product flow chart and/
Or block diagram describes various aspects of the invention.It should be appreciated that each square frame and flow chart of flow chart and/or block diagram and/
Or in block diagram each square frame combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to all-purpose computer, special-purpose computer or other programmable datas
The processor of processing unit, so as to produce a kind of machine so that these instructions are by computer or other programmable datas
During the computing device of processing unit, work(specified in one or more square frames realized in flow chart and/or block diagram is generated
The device of energy/action.Can also be the storage of these computer-readable program instructions in a computer-readable storage medium, these refer to
Order causes that computer, programmable data processing unit and/or other equipment work in a specific way, so that, be stored with instruction
Computer-readable medium then includes a manufacture, and it includes realizing in one or more square frames in flow chart and/or block diagram
The instruction of the various aspects of the function/action of regulation.
Can also computer-readable program instructions be loaded into computer, other programmable data processing units or other
In equipment so that perform series of operation steps on computer, other programmable data processing units or miscellaneous equipment, to produce
The computer implemented process of life, so that performed on computer, other programmable data processing units or miscellaneous equipment
Instruct function/action specified in one or more square frames realized in flow chart and/or block diagram.
Flow chart and block diagram in accompanying drawing show system, method and the computer journey of multiple embodiments of the invention
The architectural framework in the cards of sequence product, function and operation.At this point, each square frame in flow chart or block diagram can generation
One part for module, program segment or instruction of table a, part for the module, program segment or instruction is used comprising one or more
In the executable instruction of the logic function for realizing regulation.In some realizations as replacement, the function of being marked in square frame
Can occur with different from the order marked in accompanying drawing.For example, two continuous square frames can essentially be held substantially in parallel
OK, they can also be performed in the opposite order sometimes, and this is depending on involved function.It is also noted that block diagram and/or
The combination of the square frame in each square frame and block diagram and/or flow chart in flow chart, can use the function of performing regulation or dynamic
The special hardware based system made is realized, or can be realized with the combination of computer instruction with specialized hardware.
It is described above various embodiments of the present invention, described above is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.In the case of without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes will be apparent from for the those of ordinary skill in art field.The selection of term used herein, purport
Best explaining principle, practical application or the technological improvement to the technology in market of each embodiment, or lead this technology
Other those of ordinary skill in domain are understood that each embodiment disclosed herein.
Claims (18)
1. a kind of video recording method, it is characterised in that including：
Each two field picture of the video to being played carries out facial characteristics identification frame by frame；
The position for recording mask and size in each two field picture are determined according to facial characteristics recognition result；And
Position and size according to the record mask in each two field picture are recorded to the video.
2. video recording method according to claim 1, it is characterised in that determined according to facial characteristics recognition result
The position of the record mask in each two field picture and size, including：
The position for recording mask and original dimension in each two field picture are determined according to facial characteristics recognition result；
One of size is selected from each original dimension determined as reference dimension；And
The original dimension of the record mask in each two field picture is adjusted to the reference dimension.
3. video recording method according to claim 2, it is characterised in that the reference dimension is according to the video
The resolution ratio of each two field picture and pre-set.
4. video recording method according to claim 1, it is characterised in that determined according to facial characteristics recognition result
The position of the record mask in each two field picture and size, including：
In the case of the facial characteristics that multiple objects are identified from a two field picture of the video first, from the multiple right
As at least one object of middle selection is used as perpetual object；
In the follow-up two field picture of a two field picture, determine frame by frame and the facial characteristics of each object in the perpetual object
The matching facial characteristics of similarity corresponding objects respectively below predetermined similarity threshold；And
The facial characteristics of each object in the perpetual object and the matching facial characteristics of each corresponding objects determine respectively
The position of the record mask in a two field picture and the follow-up two field picture and size.
5. video recording method according to claim 4, it is characterised in that also include：
Continue in the rear in two field picture, if there is the two field picture without the matching facial characteristics, then basis is described respectively
The facial characteristics of each object in perpetual object and the matching facial characteristics of each corresponding objects come determine from a two field picture to
The position of the record mask in two field picture between the two field picture without the matching facial characteristics and size.
6. video recording method according to claim 4, it is characterised in that each right in the perpetual object respectively
The matching facial characteristics of the facial characteristics of elephant and each corresponding objects determines in a two field picture and the follow-up two field picture
Record mask position and size, including：
The facial characteristics of each object in the perpetual object and the matching facial characteristics of each corresponding objects determine respectively
The position of the record mask in a two field picture and the follow-up two field picture and original dimension；
One of size is selected from each original dimension determined as reference dimension；And
Original dimension in a two field picture and the follow-up two field picture is adjusted to the reference dimension.
7. video recording method according to claim 6, it is characterised in that the reference dimension is according to the video
The resolution ratio of each two field picture and pre-set.
8. video recording method according to any one of claim 1 to 7, it is characterised in that according in each frame figure
The position of the record mask as in and size are recorded to the video, including：
Default expression is loaded into the record mask；And
The position of the record mask according to the expression for being loaded and in each two field picture and size are recorded to the video
System.
9. video recording method according to any one of claim 1 to 8, it is characterised in that to the video played
Each two field picture carries out facial characteristics identification frame by frame, including：To the facial key area in each two field picture of the video played
Position is positioned,
Wherein, the critical zone locations include eyebrow, eyes, nose, face, ear and face mask region in extremely
It is few one.
10. a kind of video recording device, it is characterised in that including：
Facial characteristics recognition unit, each two field picture for the video to being played carries out facial characteristics identification frame by frame；
Determining unit, is connected, with the facial characteristics recognition unit for being determined described according to facial characteristics recognition result
The position of the record mask in each two field picture and size；And
Record screen unit, is connected with the determining unit, the position for recording mask in each two field picture and size for basis
To be recorded to the video.
11. video recording devices according to claim 10, it is characterised in that the determining unit includes：
First determining module, the position for determining the record mask in each two field picture according to facial characteristics recognition result
And original dimension；
First choice module, is connected with first determining module, for being selected wherein from each original dimension determined
One size is used as reference dimension；And
Adjusting module, is connected with the first choice module, for by each two field picture record mask original dimension
It is adjusted to the reference dimension.
12. video recording devices according to claim 11, it is characterised in that the reference dimension is according to the video
Each two field picture resolution ratio and pre-set.
13. video recording devices according to claim 9, it is characterised in that the determining unit includes：
Second selecting module, for the feelings in the facial characteristics that multiple objects are first identified from a two field picture of the video
Under condition, at least one object is selected from the multiple object as perpetual object；
Second determining module, is connected with second selecting module, in the follow-up two field picture of a two field picture, frame by frame
It is determined that with the perpetual object in each object facial characteristics similarity it is right below predetermined similarity threshold respectively
Tackle the matching facial characteristics of elephant；And
3rd determining module, is connected with second determining module, for each object respectively in the perpetual object
The matching facial characteristics of facial characteristics and each corresponding objects determines the record in a two field picture and the follow-up two field picture
The position of mask and size.
14. video recording devices according to claim 13, it is characterised in that the 3rd determining module is additionally operable to：
Continue in the rear in two field picture, if there is the two field picture without the matching facial characteristics, then basis is described respectively
The facial characteristics of each object in perpetual object and the matching facial characteristics of each corresponding objects come determine from a two field picture to
The position of the record mask in two field picture between the two field picture without the matching facial characteristics and size.
15. video recording devices according to claim 13, it is characterised in that the 3rd determining module is used for：
The facial characteristics of each object in the perpetual object and the matching facial characteristics of each corresponding objects determine respectively
The position of the record mask in a two field picture and the follow-up two field picture and original dimension；
One of size is selected from each original dimension determined as reference dimension；And
Original dimension in a two field picture and the follow-up two field picture is adjusted to the reference dimension.
16. video recording devices according to claim 15, it is characterised in that the reference dimension is according to the video
Each two field picture resolution ratio and pre-set.
17. video recording device according to any one of claim 10 to 16, it is characterised in that the record screen unit bag
Include：
Load-on module, for default expression to be loaded into the record mask；And
Record panel module, is connected, for according to the expression for being loaded and the record screen in each two field picture with the load-on module
The position of frame and size are recorded to the video.
18. video recording device according to any one of claim 10 to 17, it is characterised in that the facial characteristics is known
Other unit is used for：Facial critical zone locations in each two field picture of the video played are positioned,
Wherein, the critical zone locations include eyebrow, eyes, nose, face, ear and face mask region in extremely
It is few one.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611071695.8A CN106791535B (en) | 2016-11-28 | 2016-11-28 | Video recording method and device |
| PCT/CN2017/111075 WO2018095252A1 (en) | 2016-11-28 | 2017-11-15 | Video recording method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611071695.8A CN106791535B (en) | 2016-11-28 | 2016-11-28 | Video recording method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106791535A true CN106791535A (en) | 2017-05-31 |
| CN106791535B CN106791535B (en) | 2020-07-14 |
Family
ID=58902567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611071695.8A Active CN106791535B (en) | 2016-11-28 | 2016-11-28 | Video recording method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106791535B (en) |
| WO (1) | WO2018095252A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018095252A1 (en) * | 2016-11-28 | 2018-05-31 | 优酷网络技术（北京）有限公司 | Video recording method and device |
| CN109218612A (en) * | 2018-09-17 | 2019-01-15 | 东莞市丰展电子科技有限公司 | A kind of tracking camera system and image pickup method |
| CN109982109A (en) * | 2019-04-03 | 2019-07-05 | 睿魔智能科技（深圳）有限公司 | The generation method and device of short-sighted frequency, server and storage medium |
| CN112714253A (en) * | 2020-12-28 | 2021-04-27 | 维沃移动通信有限公司 | Video recording method and device, electronic equipment and readable storage medium |
| WO2022057602A1 (en) * | 2020-09-15 | 2022-03-24 | 深圳市万普拉斯科技有限公司 | Terminal control method and apparatus, electronic device, and storage medium |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615309B (en) * | 2018-09-25 | 2022-11-01 | 创新先进技术有限公司 | Data recording method and device, computing equipment and storage medium |
| CN112307925B (en) * | 2020-10-23 | 2023-11-28 | 腾讯科技（深圳）有限公司 | Image detection method, image display method, related device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101388981A (en) * | 2007-09-10 | 2009-03-18 | 株式会社东芝 | Video image processing apparatus and video image processing method |
| CN102693739A (en) * | 2011-03-24 | 2012-09-26 | 腾讯科技（深圳）有限公司 | Method and system for video clip generation |
| US20130243269A1 (en) * | 2012-03-19 | 2013-09-19 | Next Level Security Systems, Inc. | Distributive facial matching and notification system |
| CN103679155A (en) * | 2013-12-30 | 2014-03-26 | 深圳锐取信息技术股份有限公司 | Multi-target automatic tracking system and method |
| CN105872438A (en) * | 2015-12-15 | 2016-08-17 | 乐视致新电子科技（天津）有限公司 | Video call method and device, and terminal |
| CN106028090A (en) * | 2016-05-23 | 2016-10-12 | 努比亚技术有限公司 | Mobile terminal and video recording method thereof |
| CN106101767A (en) * | 2016-07-28 | 2016-11-09 | 维沃移动通信有限公司 | A kind of screen recording method and mobile terminal |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5942586B2 (en) * | 2012-05-18 | 2016-06-29 | 富士通株式会社 | Tablet terminal and operation reception program |
| JP2015194997A (en) * | 2014-03-27 | 2015-11-05 | キヤノンマーケティングジャパン株式会社 | User interface device, user interface method, program and recording medium |
| CN104796781B (en) * | 2015-03-31 | 2019-01-18 | 小米科技有限责任公司 | Video clip extracting method and device |
| CN104967802B (en) * | 2015-04-29 | 2019-07-19 | 努比亚技术有限公司 | The method for recording and device of mobile terminal and its plurality of regions on screen |
| CN106791535B (en) * | 2016-11-28 | 2020-07-14 | 阿里巴巴（中国）有限公司 | Video recording method and device |
-
2016
- 2016-11-28 CN CN201611071695.8A patent/CN106791535B/en active Active
-
2017
- 2017-11-15 WO PCT/CN2017/111075 patent/WO2018095252A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101388981A (en) * | 2007-09-10 | 2009-03-18 | 株式会社东芝 | Video image processing apparatus and video image processing method |
| CN102693739A (en) * | 2011-03-24 | 2012-09-26 | 腾讯科技（深圳）有限公司 | Method and system for video clip generation |
| US20130243269A1 (en) * | 2012-03-19 | 2013-09-19 | Next Level Security Systems, Inc. | Distributive facial matching and notification system |
| CN103679155A (en) * | 2013-12-30 | 2014-03-26 | 深圳锐取信息技术股份有限公司 | Multi-target automatic tracking system and method |
| CN105872438A (en) * | 2015-12-15 | 2016-08-17 | 乐视致新电子科技（天津）有限公司 | Video call method and device, and terminal |
| CN106028090A (en) * | 2016-05-23 | 2016-10-12 | 努比亚技术有限公司 | Mobile terminal and video recording method thereof |
| CN106101767A (en) * | 2016-07-28 | 2016-11-09 | 维沃移动通信有限公司 | A kind of screen recording method and mobile terminal |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018095252A1 (en) * | 2016-11-28 | 2018-05-31 | 优酷网络技术（北京）有限公司 | Video recording method and device |
| CN109218612A (en) * | 2018-09-17 | 2019-01-15 | 东莞市丰展电子科技有限公司 | A kind of tracking camera system and image pickup method |
| CN109218612B (en) * | 2018-09-17 | 2022-04-22 | 东莞市丰展电子科技有限公司 | Tracking shooting system and shooting method |
| CN109982109A (en) * | 2019-04-03 | 2019-07-05 | 睿魔智能科技（深圳）有限公司 | The generation method and device of short-sighted frequency, server and storage medium |
| CN109982109B (en) * | 2019-04-03 | 2021-08-03 | 睿魔智能科技（深圳）有限公司 | Short video generation method and device, server and storage medium |
| WO2022057602A1 (en) * | 2020-09-15 | 2022-03-24 | 深圳市万普拉斯科技有限公司 | Terminal control method and apparatus, electronic device, and storage medium |
| CN112714253A (en) * | 2020-12-28 | 2021-04-27 | 维沃移动通信有限公司 | Video recording method and device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106791535B (en) | 2020-07-14 |
| WO2018095252A1 (en) | 2018-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106791535A (en) | Video recording method and device | |
| CN106792170A (en) | Method for processing video frequency and device | |
| CN106792075A (en) | Video broadcasting method and device | |
| CN108985176A (en) | image generating method and device | |
| CN108093315A (en) | Video generation method and device | |
| CN110121083A (en) | The generation method and device of barrage | |
| CN107948708A (en) | Barrage methods of exhibiting and device | |
| CN108259991A (en) | Method for processing video frequency and device | |
| CN109729435A (en) | The extracting method and device of video clip | |
| CN106993229A (en) | Interactive attribute methods of exhibiting and device | |
| CN106559712A (en) | Video playback processing method, device and terminal device | |
| CN106960014A (en) | Association user recommends method and device | |
| CN108924644A (en) | Video clip extracting method and device | |
| CN109963168A (en) | Video previewing method and device | |
| CN109407944A (en) | Multimedia resource plays adjusting method and device | |
| CN107820131A (en) | Share the method and device of comment information | |
| CN110519655A (en) | Video clipping method and device | |
| CN108062364A (en) | Information displaying method and device | |
| CN107122430A (en) | Search result display methods and device | |
| CN108156506A (en) | The progress adjustment method and device of barrage information | |
| CN107943550A (en) | Method for showing interface and device | |
| CN110121106A (en) | Video broadcasting method and device | |
| CN108259974A (en) | Video matching method and device | |
| CN109359218A (en) | Multimedia resource methods of exhibiting and device | |
| CN106254939A (en) | Information cuing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1238053 Country of ref document: HK |
|
| CB02 | Change of applicant information |
Address after: 100080 Beijing Haidian District city Haidian street A Sinosteel International Plaza No. 8 block 5 layer A, C Applicant after: Youku network technology (Beijing) Co.,Ltd. Address before: 100080 area a and C, 5 / F, block a, Sinosteel International Plaza, No. 8, Haidian Street, Haidian District, Beijing Applicant before: 1VERGE INTERNET TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200617 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 100080 Beijing Haidian District city Haidian street A Sinosteel International Plaza No. 8 block 5 layer A, C Applicant before: Youku network technology (Beijing) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240624 Address after: 101400 Room 201, 9 Fengxiang East Street, Yangsong Town, Huairou District, Beijing Patentee after: Youku Culture Technology (Beijing) Co.,Ltd. Country or region after: China Address before: 310052 room 508, 5th floor, building 4, No. 699 Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Patentee before: Alibaba (China) Co.,Ltd. Country or region before: China |