CN109241345A - Video locating method and device based on recognition of face - Google Patents
Video locating method and device based on recognition of face Download PDFInfo
- Publication number
- CN109241345A CN109241345A CN201811178561.5A CN201811178561A CN109241345A CN 109241345 A CN109241345 A CN 109241345A CN 201811178561 A CN201811178561 A CN 201811178561A CN 109241345 A CN109241345 A CN 109241345A
- Authority
- CN
- China
- Prior art keywords
- image
- frame image
- facial image
- frame
- video
- 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
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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present invention proposes a kind of video locating method and device based on recognition of face.This method comprises: each frame image to video carries out recognition of face, each frame image including facial image is obtained；Target following is carried out to each frame image for including facial image, is gathered each frame image of the facial image including same personage as one；Multiple frame images are chosen from each set；Compare the facial image of target person with from the facial image in each frame image that each set is chosen, the position occurred in the video with the determination target person.The embodiment of the present invention can fast and accurately identify the frame image for occurring facial image in video, also, targetedly identify that the facial image of target person occurs in which frame image.Therefore, be conducive to assist video editing, processing is optimized to video.
Description
Technical field
The present invention relates to technical field of face recognition more particularly to a kind of video locating methods and dress based on recognition of face
It sets.
Background technique
In a video, various personage may include.These personages may go out in certain times of video playing
Existing, certain times do not occur.If necessary to fall some character image editings in video, needs to edit and manually check the view
Frequently, in the character image that discovery needs to be clipped to, the information such as time which occurs are recorded, then is cut
Collect operation.
Time-consuming for the artificial character image checked in video, if certain scene conversions in video are too fast, is also easy to leak
Fall to want the character image cut.
Summary of the invention
The embodiment of the present invention provides a kind of video locating method and device based on recognition of face, to solve in the prior art
One or more technical problems.
In a first aspect, the embodiment of the invention provides a kind of video locating methods based on recognition of face, comprising:
Recognition of face is carried out to each frame image of video, obtains each frame image including facial image；
Target following is carried out to each frame image for including facial image, by each frame figure of the facial image including same personage
As a set；
Multiple frame images are chosen from each set；
Compare the facial image of target person with from the facial image in each frame image that each set is chosen, to determine
State the position that target person occurs in the video.
In one embodiment, target following is carried out to each frame image for including facial image, comprising:
Using core correlation filtering, target following is carried out to each frame image for including facial image.
In one embodiment, using core correlation filtering, target is carried out to each frame image for including facial image
Tracking, comprising:
Detect position of the facial image in each frame image；
Calculate position offset of the facial image in consecutive frame image；
If position offset be less than given threshold, the consecutive frame image is determined as include same personage face
The frame image of image.
In one embodiment, position offset of the facial image in consecutive frame image is calculated, comprising:
If consecutive frame image occurs stretching or scale, after the coordinate alignment in consecutive frame image, then face is calculated
Position offset of the image in consecutive frame image.
In one embodiment, multiple frame images are chosen from each set, comprising:
According to the clarity and/or resolution ratio of the frame image for including in a set, multiple frames are chosen from the set
Image.
In one embodiment, compare the facial image of target person and from each frame image that each set is chosen
Facial image, the position occurred in the video with the determination target person, comprising:
The facial image for calculating target person and the similarity from the facial image in each frame image that each set is chosen；
If the facial image of target person and the similarity from the facial image in each frame image that a set is chosen
Greater than given threshold, it is determined that the target person occurs in the set of the video；
Obtain the frame number and/or corresponding playing time for occurring that the set of the target person includes.
Second aspect, the embodiment of the invention provides a kind of video positioning apparatus based on recognition of face, comprising:
Face recognition module carries out recognition of face for each frame image to video, obtains each frame including facial image
Image；
Target tracking module will include same personage for carrying out target following to each frame image for including facial image
Facial image each frame image as one gather；
Module is chosen, for choosing multiple frame images from each set；
Locating module, for compare the facial image of target person with from the face in each frame image that each set is chosen
Image, the position occurred in the video with the determination target person.
In one embodiment, the target tracking module is also used to using core correlation filtering, to including face
Each frame image of image carries out target following.
In one embodiment, the target tracking module is also used to detect position of the facial image in each frame image
It sets；Calculate position offset of the facial image in consecutive frame image；It, will be described if position offset is less than given threshold
Consecutive frame image be determined as include the facial image of same personage frame image.
In one embodiment, if the target tracking module is also used to consecutive frame image and occurs stretching or scale,
After then the coordinate in consecutive frame image is aligned, then calculate position offset of the facial image in consecutive frame image.
In one embodiment, the clarity chosen module and be also used to the frame image for including in gathering according to one
And/or resolution ratio, multiple frame images are chosen from the set.
In one embodiment, the locating module be also used to calculate the facial image of target person with from each set
The similarity for the facial image in each frame image chosen；If the facial image of target person gathers each of selection with from one
The similarity of facial image in frame image is greater than given threshold, it is determined that the set of the target person in the video
Middle appearance；Obtain the frame number and/or corresponding playing time for occurring that the set of the target person includes.
The third aspect, the embodiment of the invention provides a kind of video positioning apparatus based on recognition of face, described device
Function can also execute corresponding software realization by hardware realization by hardware.The hardware or software include one
Or multiple modules corresponding with above-mentioned function.
It include processor and memory in the structure of described device in a possible design, the memory is used for
Storage supports described device to execute the program of the above-mentioned video locating method based on recognition of face, the processor is configured to
The program stored in the execution memory.Described device can also include communication interface, be used for and other equipment or communication
Network communication.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage mediums, are known for storing based on face
Computer software instructions used in other video positioning apparatus comprising for executing the above-mentioned video location based on recognition of face
Program involved in method.
A technical solution in above-mentioned technical proposal has the following advantages that or the utility model has the advantages that can fast and accurately know
The frame image of facial image Chu not occur in video, also, targetedly identify the facial image of target person at which
Occur in frame image.Therefore, be conducive to assist video editing, processing is optimized to video.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to be limited in any way.Except foregoing description
Schematical aspect, except embodiment and feature, by reference to attached drawing and the following detailed description, the present invention is further
Aspect, embodiment and feature, which will be, to be readily apparent that.
Detailed description of the invention
In the accompanying drawings, unless specified otherwise herein, otherwise indicate the same or similar through the identical appended drawing reference of multiple attached drawings
Component or element.What these attached drawings were not necessarily to scale.It should be understood that these attached drawings depict only according to the present invention
Disclosed some embodiments, and should not serve to limit the scope of the present invention.
Fig. 1 shows the flow chart of the video locating method according to an embodiment of the present invention based on recognition of face.
Fig. 2 shows the flow charts of the video locating method according to an embodiment of the present invention based on recognition of face.
Fig. 3 shows the flow chart of the video locating method according to an embodiment of the present invention based on recognition of face.
Fig. 4 shows the structural block diagram of the video positioning apparatus according to an embodiment of the present invention based on recognition of face.
Fig. 5 shows the structural block diagram of the video positioning apparatus according to an embodiment of the present invention based on recognition of face.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize that
Like that, without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes.
Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
Fig. 1 shows the flow chart of the video locating method according to an embodiment of the present invention based on recognition of face.Such as Fig. 1 institute
Show, being somebody's turn to do the video locating method based on recognition of face may include:
Step S11, recognition of face is carried out to each frame image of video, obtains each frame image including facial image.
Step S12, target following is carried out to each frame image for including facial image, by the facial image including same personage
Each frame image as one gather.
Step S13, multiple frame images are chosen from each set.
Step S14, compare the facial image of target person with from the facial image in each frame image that each set is chosen,
The position occurred in the video with the determination target person.
In general, video includes several frame image, and each frame image has corresponding frame number.In general, each frame figure
As also having corresponding playing time in video.There is landscape in some frame images, there is personage in some frame images.Having
Have in the frame image of personage, the facial image in some frame images there may be one, and the facial image in some frame images may
Have multiple.
In embodiments of the present invention, recognition of face can be carried out to all frame images of video, it can also be first to video
The frame image of a part for example preceding 10% carries out recognition of face, then carries out recognition of face to subsequent frame image segmentation.In this way, can
The frame optical sieving in video including facial image to be come out.
In one embodiment, in step s 12, target following, packet are carried out to each frame image for including facial image
It includes: using core KCF (Kernel Correlation Filter core correlation filtering) algorithm, to each frame figure including facial image
As carrying out target following.It is then possible to gather each frame image of the facial image including same personage as one, may obtain
To multiple set.
For example, frame number 040 to 050 includes the face of personage B if frame number 010 to 030 includes the facial image of personage A
Image, using the frame image of frame number 010 to 030 as a set S1, the frame image of frame number 040 to 050 is as a set S2.
The facial image of multiple personages is likely to occur in one frame image, therefore, the same frame image may belong to difference
Set.For example, frame number 020 to 050 includes the face figure of personage C if frame number 010 to 030 includes the facial image of personage A
Picture, using the frame image of frame number 010 to 030 as a set S1, the frame image of frame number 020 to 050 is as a set S3.
In one embodiment, as shown in Fig. 2, using core correlation filtering, to each frame figure including facial image
As carrying out target following, comprising:
Step S21, position of the detection facial image in each frame image.
Step S22, position offset of the facial image in consecutive frame image is calculated.
If step S23, position offset is less than given threshold, the consecutive frame image is determined as including same people
The frame image of the facial image of object.
In embodiments of the present invention, these can be determined according to position offset of the facial image in each frame image
Whether the facial image for including in frame image belongs to same personage.The position that usual same personage occurs in consecutive frame image is inclined
Shifting amount will not be too far.Therefore position offset of the facial image in consecutive frame image can be calculated.If the difference is less than one
Determine threshold value, it is possible to determine that consecutive frame image determines the facial image including same personage.
In a kind of example, calculating position offset of the facial image in consecutive frame image may include: calculating face
The difference or distance of center point coordinate of the image in consecutive frame image.Such as: the centre coordinate of facial image in frame image F1
For (x1, y1), the centre coordinate of facial image is (x2, y2) in frame image F2, and the difference of the two can be (x2-x1, y2-
y1).The two distance can be Euclidean distance or COS distance etc..
In another example, calculating position offset of the facial image in consecutive frame image may include: to calculate people
After the difference of center point coordinate of the face image in consecutive frame image, then calculate the ratio of the difference and frame image size.For example,
The centre coordinate of facial image is (x1, y1) in frame image F1, and the centre coordinate of facial image is (x2, y2) in frame image F2,
The difference of the two can be (x2-x1, y2-y1).If the length of frame image is x, width y can calculate ratio (x2-
X1)/x, and (y2-y1)/y, using these ratios as offset.
Therefore, offset threshold value can also be arranged in correspondence with according to the calculation method of offset.For example, setting length difference
Threshold value, the threshold value of width difference, the threshold value of Euclidean distance, proportion threshold value etc..
In one embodiment, position offset of the facial image in consecutive frame image is calculated, comprising:
If consecutive frame image occurs stretching or scale, after the coordinate alignment in consecutive frame image, then face is calculated
Position offset of the image in consecutive frame image.
During video capture, in fact it could happen that the stretching of camera lens or scaling so that same facial image generate amplification or
The block that person reduces.For example, if frame image F1 and F2 are consecutive frame image, also, frame image F2 goes out compared with frame image F1
Stretching is showed, then coordinate conversion first can have been carried out to F2 according to the ratio of stretching, then compare the position of facial image in F2 and F1
Offset.
In one embodiment, step S13 chooses multiple frame images from each set, comprising:
According to the clarity and/or resolution ratio of the frame image for including in a set, multiple frames are chosen from the set
Image.
For example, including 20 frame images in some set, the high example of several image quality can be chosen from this 20 frame images
Such as high resolution and the high frame image of clarity.In this way, being conducive to accurately be known in subsequent progress target person identification
Other result.
In one embodiment, as shown in figure 3, step S14 compare the facial image of target person with from each set
The facial image in each frame image chosen, the position occurred in the video with the determination target person, comprising:
Step S31, calculate target person facial image with from it is each set choose each frame image in facial image
Similarity.
If step S32, the facial image of target person and the facial image gathered in each frame image chosen from one
Similarity be greater than given threshold, it is determined that the target person occurs in the set of the video.
Step S33, the frame number and/or corresponding playing time for occurring that the set of the target person includes are obtained.
If all including the facial image of target person from all frame images chosen in some set, it is possible to determine that this
The frame image maximum probability for including in a set belongs to this target person.Wherein, the facial image of target person can be by user
It voluntarily provides, some personages can be prestored in the database, such as need to forbid the photo etc. of the blacklist personage played.It is needing
It, can be real to recall the facial images of one or more target persons in database when carrying out the processing such as editing to some video
Existing real time contrast.
For example, the frame image in video including human face region has 100 facial images for same personage occur, by this 100
Zhang Zuowei mono- set.The frame image that several image quality height (high resolution, clarity are high) can be selected from this set, than
The similarity of the facial image of the frame image and target person relatively selected.If similarity height can be determined that this 100 frame images
In include target person.
It is then possible to export the frame number of these frame images with target person.Exist in addition it is also possible to export these frame numbers
Corresponding playing time in video.
In a kind of application example, in the post-production of video, recognition of face is carried out to video, obtains some target person
Object occur frame number or after the moment, these frame images can be found, the target person in these frame images is handled.Example
Such as, these frame images are deleted, or mosaic processing etc. is done to the target person in these frame images.
Using the embodiment of the present invention, it can fast and accurately identify occur the frame image of facial image in video, and
And targetedly identify that the facial image of target person occurs in which frame image.Therefore, be conducive to that video is assisted to compile
Volume, processing is optimized to video.
The embodiment of the present invention can both have been supported to automatically track using personage in database realizing video, can also support to use
Family uploads the character image to be tracked.In addition, by the personage in identification video, number that position character occurs in video,
The position etc. occurred every time, convenient for handling specific personage in the post-production of video.
Fig. 4 shows the structural block diagram of the video positioning apparatus according to an embodiment of the present invention based on recognition of face.Such as Fig. 4 institute
Show, the apparatus may include:
Face recognition module 41 carries out recognition of face for each frame image to video, and obtaining includes each of facial image
Frame image；
Target tracking module 42 will include same people for carrying out target following to each frame image for including facial image
Each frame image of the facial image of object is gathered as one；
Module 43 is chosen, for choosing multiple frame images from each set；
Locating module 44, for compare the facial image of target person with from the people in each frame image that each set is chosen
Face image, the position occurred in the video with the determination target person.
In one embodiment, the target tracking module 42 is also used to using core correlation filtering, to including people
Each frame image of face image carries out target following.
In one embodiment, the target tracking module 42 is also used to detect position of the facial image in each frame image
It sets；Calculate position offset of the facial image in consecutive frame image；It, will be described if position offset is less than given threshold
Consecutive frame image be determined as include the facial image of same personage frame image.
In one embodiment, if the target tracking module 42 is also used to consecutive frame image and occurs stretching or contract
It puts, then after being aligned the coordinate in consecutive frame image, then calculates position offset of the facial image in consecutive frame image.
In one embodiment, the module 43 of choosing is also used to according to the clear of the frame image for including in a set
Degree and/or resolution ratio, choose multiple frame images from the set.
In one embodiment, the locating module 44 be also used to calculate the facial image of target person with from each collection
Close the similarity of the facial image in each frame image chosen；If the facial image of target person gathers selection with from one
The similarity of facial image in each frame image is greater than given threshold, it is determined that the collection of the target person in the video
Occur in conjunction；Obtain the frame number and/or corresponding playing time for occurring that the set of the target person includes.
The function of each module in each device of the embodiment of the present invention may refer to the corresponding description in the above method, herein not
It repeats again.
Fig. 5 shows the structural block diagram of the video positioning apparatus according to an embodiment of the present invention based on recognition of face.Such as Fig. 5 institute
Show, which includes: memory 910 and processor 920, and the calculating that can be run on processor 920 is stored in memory 910
Machine program.The processor 920 realizes that the affairs in above-described embodiment submit method when executing the computer program.It is described to deposit
The quantity of reservoir 910 and processor 920 can be one or more.
The device further include:
Communication interface 930 carries out data interaction for being communicated with external device.
Memory 910 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-
Volatile memory), a for example, at least magnetic disk storage.
If memory 910, processor 920 and the independent realization of communication interface 930, memory 910,920 and of processor
Communication interface 930 can be connected with each other by bus and complete mutual communication.The bus can be Industry Standard Architecture
Structure (ISA, Industry Standard Architecture) bus, external equipment interconnection (PCI, Peripheral
Component) bus or extended industry-standard architecture (EISA, Extended Industry Standard
Component) bus etc..The bus can be divided into address bus, data/address bus, control bus etc..For convenient for expression, Fig. 5
In only indicated with a thick line, it is not intended that an only bus or a type of bus.
Optionally, in specific implementation, if memory 910, processor 920 and communication interface 930 are integrated in one piece of core
On piece, then memory 910, processor 920 and communication interface 930 can complete mutual communication by internal interface.
The embodiment of the invention provides a kind of computer readable storage mediums, are stored with computer program, the program quilt
Processor realizes any method in above-described embodiment when executing.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hidden
It include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise
Clear specific restriction.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, to execute function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable read-only memory
(CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other suitable Jie
Matter, because can then be edited, be interpreted or when necessary with other for example by carrying out optical scanner to paper or other media
Suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In readable storage medium storing program for executing.The storage medium can be read-only memory, disk or CD etc..
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in its various change or replacement,
These should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the guarantor of the claim
It protects subject to range.
Claims (14)
1. a kind of video locating method based on recognition of face characterized by comprising
Recognition of face is carried out to each frame image of video, obtains each frame image including facial image；
Target following is carried out to each frame image for including facial image, each frame image of the facial image including same personage is made
Gather for one；
Multiple frame images are chosen from each set；
Compare the facial image of target person with from the facial image in each frame image that each set is chosen, with the determination mesh
The position that mark personage occurs in the video.
2. the method according to claim 1, wherein to include facial image each frame image carry out target with
Track, comprising:
Using core correlation filtering, target following is carried out to each frame image for including facial image.
3. according to the method described in claim 2, it is characterized in that, using core correlation filtering, to including facial image
Each frame image carries out target following, comprising:
Detect position of the facial image in each frame image；
Calculate position offset of the facial image in consecutive frame image；
If position offset be less than given threshold, the consecutive frame image is determined as include same personage facial image
Frame image.
4. according to the method described in claim 3, it is characterized in that, calculating positional shift of the facial image in consecutive frame image
Amount, comprising:
If consecutive frame image occurs stretching or scale, after the coordinate alignment in consecutive frame image, then facial image is calculated
Position offset in consecutive frame image.
5. method according to claim 1 to 4, which is characterized in that choose multiple frame figures from each set
Picture, comprising:
According to the clarity and/or resolution ratio of the frame image for including in a set, multiple frame images are chosen from the set.
6. method according to claim 1 to 4, which is characterized in that compare the facial image of target person with
Facial image from each frame image that each set is chosen, the position occurred in the video with the determination target person
It sets, comprising:
The facial image for calculating target person and the similarity from the facial image in each frame image that each set is chosen；
If the facial image of target person is greater than with from the similarity of the facial image in each frame image that a set is chosen
Given threshold, it is determined that the target person occurs in the set of the video；
Obtain the frame number and/or corresponding playing time for occurring that the set of the target person includes.
7. a kind of video positioning apparatus based on recognition of face characterized by comprising
Face recognition module carries out recognition of face for each frame image to video, obtains each frame image including facial image；
Target tracking module, for carrying out target following to each frame image for including facial image, by the people including same personage
Each frame image of face image is gathered as one；
Module is chosen, for choosing multiple frame images from each set；
Locating module, for compare the facial image of target person with from the face figure in each frame image that each set is chosen
Picture, the position occurred in the video with the determination target person.
8. device according to claim 7, which is characterized in that the target tracking module is also used to using core correlation filtering
Algorithm carries out target following to each frame image for including facial image.
9. device according to claim 8, which is characterized in that the target tracking module is also used to detect facial image and exists
Position in each frame image；Calculate position offset of the facial image in consecutive frame image；It is set if position offset is less than
Determine threshold value, then the consecutive frame image is determined as include the facial image of same personage frame image.
10. device according to claim 9, which is characterized in that if the target tracking module is also used to consecutive frame figure
As occurring stretching or scale, then after being aligned the coordinate in consecutive frame image, then facial image is calculated in consecutive frame image
Position offset.
11. device according to any one of claims 7 to 10, which is characterized in that the selection module is also used to basis
The clarity and/or resolution ratio for the frame image for including in one set, choose multiple frame images from the set.
12. device according to any one of claims 7 to 10, which is characterized in that the locating module is also used to calculate
The facial image of target person and the similarity from the facial image in each frame image that each set is chosen；If target person
Facial image with from one set choose each frame image in facial image similarity be greater than given threshold, it is determined that institute
Target person is stated to occur in the set of the video；Obtain occur frame number that the set of the target person includes with/
Or corresponding playing time.
13. a kind of video positioning apparatus based on recognition of face characterized by comprising
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors
Realize such as method described in any one of claims 1 to 6.
14. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the program is held by processor
Such as method described in any one of claims 1 to 6 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811178561.5A CN109241345B (en) | 2018-10-10 | 2018-10-10 | Video positioning method and device based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811178561.5A CN109241345B (en) | 2018-10-10 | 2018-10-10 | Video positioning method and device based on face recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109241345A true CN109241345A (en) | 2019-01-18 |
| CN109241345B CN109241345B (en) | 2022-10-14 |
Family
ID=65054437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811178561.5A Active CN109241345B (en) | 2018-10-10 | 2018-10-10 | Video positioning method and device based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109241345B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079670A (en) * | 2019-12-20 | 2020-04-28 | 北京百度网讯科技有限公司 | Face recognition method, face recognition device, face recognition terminal and face recognition medium |
| CN111753756A (en) * | 2020-06-28 | 2020-10-09 | 浙江大华技术股份有限公司 | Object identification-based deployment alarm method and device and storage medium |
| CN111800663A (en) * | 2019-04-09 | 2020-10-20 | 阿里巴巴集团控股有限公司 | Video synthesis method and device |
| CN111835985A (en) * | 2019-04-16 | 2020-10-27 | 阿里巴巴集团控股有限公司 | Video editing method, device, apparatus and storage medium |
| CN112203142A (en) * | 2020-12-03 | 2021-01-08 | 浙江岩华文化科技有限公司 | Video processing method and device, electronic device and storage medium |
| CN113392810A (en) * | 2021-07-08 | 2021-09-14 | 北京百度网讯科技有限公司 | Method, apparatus, device, medium and product for in vivo detection |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101567043A (en) * | 2009-05-31 | 2009-10-28 | 中山大学 | Face tracking method based on classification and identification |
| JP2011170711A (en) * | 2010-02-19 | 2011-09-01 | Toshiba Corp | Moving object tracking system and moving object tracking method |
| CN102306290A (en) * | 2011-10-14 | 2012-01-04 | 刘伟华 | Face tracking recognition technique based on video |
| CN104731964A (en) * | 2015-04-07 | 2015-06-24 | 上海海势信息科技有限公司 | Face abstracting method and video abstracting method based on face recognition and devices thereof |
| CN104796781A (en) * | 2015-03-31 | 2015-07-22 | 小米科技有限责任公司 | Video clip extraction method and device |
| CN106127106A (en) * | 2016-06-13 | 2016-11-16 | 东软集团股份有限公司 | Target person lookup method and device in video |
| WO2017080399A1 (en) * | 2015-11-12 | 2017-05-18 | 阿里巴巴集团控股有限公司 | Method and device for tracking location of human face, and electronic equipment |
| CN106874827A (en) * | 2015-12-14 | 2017-06-20 | 北京奇虎科技有限公司 | Video frequency identifying method and device |
| CN108229322A (en) * | 2017-11-30 | 2018-06-29 | 北京市商汤科技开发有限公司 | Face identification method, device, electronic equipment and storage medium based on video |
| CN108563651A (en) * | 2017-12-19 | 2018-09-21 | 深圳云天励飞技术有限公司 | A kind of Target Searching Method, device and the equipment of more videos |
-
2018
- 2018-10-10 CN CN201811178561.5A patent/CN109241345B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101567043A (en) * | 2009-05-31 | 2009-10-28 | 中山大学 | Face tracking method based on classification and identification |
| JP2011170711A (en) * | 2010-02-19 | 2011-09-01 | Toshiba Corp | Moving object tracking system and moving object tracking method |
| CN102306290A (en) * | 2011-10-14 | 2012-01-04 | 刘伟华 | Face tracking recognition technique based on video |
| CN104796781A (en) * | 2015-03-31 | 2015-07-22 | 小米科技有限责任公司 | Video clip extraction method and device |
| CN104731964A (en) * | 2015-04-07 | 2015-06-24 | 上海海势信息科技有限公司 | Face abstracting method and video abstracting method based on face recognition and devices thereof |
| WO2017080399A1 (en) * | 2015-11-12 | 2017-05-18 | 阿里巴巴集团控股有限公司 | Method and device for tracking location of human face, and electronic equipment |
| CN106874827A (en) * | 2015-12-14 | 2017-06-20 | 北京奇虎科技有限公司 | Video frequency identifying method and device |
| CN106127106A (en) * | 2016-06-13 | 2016-11-16 | 东软集团股份有限公司 | Target person lookup method and device in video |
| CN108229322A (en) * | 2017-11-30 | 2018-06-29 | 北京市商汤科技开发有限公司 | Face identification method, device, electronic equipment and storage medium based on video |
| CN108563651A (en) * | 2017-12-19 | 2018-09-21 | 深圳云天励飞技术有限公司 | A kind of Target Searching Method, device and the equipment of more videos |
Non-Patent Citations (1)
| Title |
|---|
| 李建勇: "人脸识别技术在视频监控***中的应用", 《中国安防》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111800663A (en) * | 2019-04-09 | 2020-10-20 | 阿里巴巴集团控股有限公司 | Video synthesis method and device |
| CN111835985A (en) * | 2019-04-16 | 2020-10-27 | 阿里巴巴集团控股有限公司 | Video editing method, device, apparatus and storage medium |
| CN111079670A (en) * | 2019-12-20 | 2020-04-28 | 北京百度网讯科技有限公司 | Face recognition method, face recognition device, face recognition terminal and face recognition medium |
| CN111079670B (en) * | 2019-12-20 | 2023-11-03 | 北京百度网讯科技有限公司 | Face recognition method, device, terminal and medium |
| CN111753756A (en) * | 2020-06-28 | 2020-10-09 | 浙江大华技术股份有限公司 | Object identification-based deployment alarm method and device and storage medium |
| CN112203142A (en) * | 2020-12-03 | 2021-01-08 | 浙江岩华文化科技有限公司 | Video processing method and device, electronic device and storage medium |
| CN113392810A (en) * | 2021-07-08 | 2021-09-14 | 北京百度网讯科技有限公司 | Method, apparatus, device, medium and product for in vivo detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109241345B (en) | 2022-10-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241345A (en) | Video locating method and device based on recognition of face | |
| TWI362016B (en) | Method for detecting desired objects in a highly dynamic environment by a monitoring system and the monitoring system thereof | |
| US8111266B2 (en) | Display device and method for editing images | |
| CN101601279B (en) | Imaging device, imaging method, and program | |
| JP6023058B2 (en) | Image processing apparatus, image processing method, program, integrated circuit | |
| ES2556601T3 (en) | Systems and methods for the autonomous production of videos from multiple data detected | |
| CN104135926B (en) | Image processing equipment, image processing system, image processing method and program | |
| TW200820099A (en) | Target moving object tracking device | |
| CN110378945A (en) | Depth map processing method, device and electronic equipment | |
| CN101605209A (en) | Camera head and image-reproducing apparatus | |
| AU2009243442A1 (en) | Detection of abnormal behaviour in video objects | |
| CN110427908A (en) | A kind of method, apparatus and computer readable storage medium of person detecting | |
| CN112689221B (en) | Recording method, recording device, electronic equipment and computer readable storage medium | |
| CN107944420A (en) | The photo-irradiation treatment method and apparatus of facial image | |
| CN109308465A (en) | Table line detecting method, apparatus, equipment and computer-readable medium | |
| TW201541407A (en) | Method for generating three-dimensional information from identifying two-dimensional images | |
| CN106297755A (en) | A kind of electronic equipment for musical score image identification and recognition methods | |
| CN109785348A (en) | Novel angular-point detection method and system based on the variation of image boundary approximate curvature | |
| CN108776800B (en) | Image processing method, mobile terminal and computer readable storage medium | |
| CN110717452B (en) | Image recognition method, device, terminal and computer readable storage medium | |
| CN106803886A (en) | A kind of method and device taken pictures | |
| CN109934949A (en) | Work attendance method and device, equipment, storage medium | |
| CN111669492A (en) | Method for processing shot digital image by terminal and terminal | |
| CN108875477B (en) | Exposure control method, device and system and storage medium | |
| Jinda-Apiraksa et al. | A Keyframe Selection of Lifelog Image Sequences. |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |