CN106991362A - A kind of image processing method and device for video - Google Patents
A kind of image processing method and device for video Download PDFInfo
- Publication number
- CN106991362A CN106991362A CN201610040289.9A CN201610040289A CN106991362A CN 106991362 A CN106991362 A CN 106991362A CN 201610040289 A CN201610040289 A CN 201610040289A CN 106991362 A CN106991362 A CN 106991362A
- Authority
- CN
- China
- Prior art keywords
- picture
- extraction conditions
- target video
- video
- video picture
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The embodiment of the invention discloses a kind of image processing method and device for video, wherein, methods described includes：Whether detection target video picture meets preset extraction conditions, and the target video picture includes：Obtained video has been taken, and in the picture of current time playback process or during video capture, current time shoots the picture of processing；If meeting preset extraction conditions, the target video picture is extracted；Wherein, meeting preset extraction conditions includes：The related information extracted for the target video picture meets preset extraction conditions.Using the present invention, reduce that user obtains to video pictures is manually operated, the broadcasting or recording of current video will not be interrupted because of interception picture, and can preferably meet demand of the user to required picture based on the extraction conditions that time, Drawing Object and image parameter are set, preferably meet that user extracts to video pictures automate, intellectuality demand.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of image processing method for video and
Device.
Background technology
With the development of electronic technology and computer technology, all types of is available for video, picture shooting and place
The terminal of reason is greatly popularized.It is high that people can not only use the video camera of specialty, camera to shoot
Picture, the video of quality, moreover it is possible to complete the shooting of video whenever and wherever possible by various mobile phones, play.
At present, the terminal of all kinds of achievable video captures can not carry out picture shooting when shooting video,
Video record is only cut off, exposal model is switched to.Or, terminal is when playing video, if user wants
Wherein a certain frame video pictures are, it is necessary to carry out shot operation by complicated key combination or call sectional drawing
Instrument carries out shot operation.Extraction operation of the existing mode to a certain frame picture in video is complex, no
Beneficial to user's operation.
The content of the invention
The embodiment of the present invention provides a kind of image processing method and device for video, can be quickly user
The picture for the condition that meets is extracted from video.
On the one hand, the embodiments of the invention provide a kind of image processing method for video, including：
Whether detection target video picture meets preset extraction conditions, and the target video picture includes：
Through shooting obtained video in the picture of current time playback process or when during video capture currently
Carve the picture for shooting processing；
If meeting preset extraction conditions, the target video picture is extracted；
Wherein, meeting preset extraction conditions includes：The related information extracted for the target video picture
Meet preset extraction conditions.
Wherein alternatively, the related information includes：The Drawing Object letter that the target video picture includes
Breath；Whether the detection target video picture meets preset extraction conditions, including：
Obtain the Drawing Object information that the target video picture includes；
Judge whether include one in the Drawing Object described by each Drawing Object information detected or many
The description that individual Drawing Object meets Drawing Object in the extraction conditions is indicated；
If so, then the target video picture meets preset extraction conditions.
Wherein alternatively, the related information includes：Temporal information of the target video picture in processing,
Specifically include playback process duration information or shoot handling duration information；Whether the detection target video picture
Preset extraction conditions are met, including：
Obtain temporal information of the target video picture in processing；
Judge whether temporal information of the target video picture in processing is met in preset extraction conditions
Persond eixis；
If so, then the target video picture meets preset extraction conditions.
Wherein alternatively, the related information includes：The image parameters of the target video picture, the inspection
Survey whether target video picture meets preset extraction conditions, including：
Obtain the image parameters of the target video picture；
Judge whether the image parameters of the target video picture are met in preset extraction conditions to image parameters
Demand indicate；
If so, then the target video picture meets preset extraction conditions.
Wherein alternatively, the image parameters include：The luminous flux that the Target Photo is detected when shooting
Parameter.
Wherein alternatively, before the extraction target video picture, in addition to：
Sent to user and extract prompt message, the extraction prompt message includes：Auditory tone cues information, or figure
Mark prompt message；Wherein, the icon prompt message includes：Picture is sent by the icon of preset size to carry
Prompt message is taken, the preset size is less than the size of the Target Photo.
Wherein alternatively, methods described also includes：
The video corresponding to the target video picture when quickly checking operation, will have been preserved when receiving
The picture for the corresponding video extraction be set to thumbnail and be shown to user.
The opposing party, the embodiment of the present invention accordingly provides a kind of picture processing device for video, including：
Detection module, for detecting whether target video picture meets preset extraction conditions, the target is regarded
Frequency picture includes：The video for having been taken obtaining is clapped in the picture of current time playback process or in video
Current time shoots the picture of processing during taking the photograph；
Extraction module, if for meeting preset extraction conditions, extracting the target video picture；Wherein,
Meeting preset extraction conditions includes：The related information extracted for the target video picture meets preset
Extraction conditions.
Wherein alternatively, the related information includes：The Drawing Object letter that the target video picture includes
Breath；The detection module, specifically for obtaining the Drawing Object information that the target video picture includes；
Judge whether include one or more figure in the Drawing Object described by each Drawing Object information detected
The description that shape object meets Drawing Object in the extraction conditions is indicated；If so, the then target video picture
Meet preset extraction conditions.
Wherein alternatively, the related information includes：Temporal information of the target video picture in processing,
Specifically include playback process duration information or shoot handling duration information；The detection module, specifically for obtaining
Take temporal information of the target video picture in processing；Judge the target video picture processing when
Whether temporal information meets the persond eixis in preset extraction conditions；If so, the then target video picture
Meet preset extraction conditions.
Wherein alternatively, the related information includes：The image parameters of the target video picture；The inspection
Module is surveyed, the image parameters specifically for obtaining the target video picture；Judge the target video picture
Image parameters whether meet in preset extraction conditions the demands of image parameters indicated；If so, then described
Target video picture meets preset extraction conditions.
Wherein alternatively, described device also includes：Reminding module, prompt message is extracted for being sent to user,
The extraction prompt message includes：Auditory tone cues information, or icon prompt message；Wherein, the icon is carried
Show that information includes：Picture is sent by the icon of preset size and extracts prompt message, the preset size is small
In the size of the Target Photo.
Wherein alternatively, described device also includes：Display module, is received to the target video for working as
When quickly checking operation of video corresponding to picture, by the picture for the corresponding video extraction preserved
It is set to thumbnail and is shown to user.
The embodiment of the present invention can be for video pictures come preset extraction conditions, and then are based on condition come automatic true
The fixed a certain frame video pictures whether extracted in the video recorded or the video recorded, reduce user
What video pictures were obtained is manually operated, and the broadcasting or recording of current video will not be interrupted because of interception picture,
Preferably meet that user extracts to video pictures automate, intelligent demand.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to implementing
The accompanying drawing used required in example or description of the prior art is briefly described, it should be apparent that, describe below
In accompanying drawing be only some embodiments of the present invention, for those of ordinary skill in the art, do not paying
On the premise of going out creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of image processing method for video of the embodiment of the present invention；
Fig. 2 is a kind of schematic flow sheet of image processing method for video of the embodiment of the present invention；
Fig. 3 is a kind of structural representation of picture processing device for video of the embodiment of the present invention；
Fig. 4 is a kind of structural representation of intelligent terminal of the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear
Chu, it is fully described by, it is clear that described embodiment is only a part of embodiment of the invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creation
Property work under the premise of the every other embodiment that is obtained, belong to the scope of protection of the invention.
The embodiment of the present invention can in video playback or recording process, can according to preset extraction conditions,
Therefrom extract the video pictures for meeting extraction conditions.The extraction conditions are the related informations according to video pictures
Configured, and be not based on the manually operated of user, specifically can according to the playing durations of video pictures, record
Object (such as band that parameter or the video pictures such as luminous flux when duration, the video pictures are taken include
Head portrait object of certain special expression etc.) etc. information configured.
Fig. 1 is referred to, is a kind of flow signal of image processing method for video of the embodiment of the present invention
Scheme, the methods described of the embodiment of the present invention can be realized by the intelligent terminal that can shoot and/or play video,
It is specifically as follows the terminals such as the smart mobile phone with camera function, tablet personal computer, intelligent wearable device, specifically
, methods described includes：
S101：Whether detection target video picture meets preset extraction conditions, the target video picture bag
Include：Obtained video has been taken in the picture of current time playback process or during video capture
Current time shoots the picture of processing.
S102：If meeting preset extraction conditions, the target video picture is extracted；Wherein, meet pre-
The extraction conditions put include：The related information extracted for the target video picture meets preset extraction bar
Part.
Extraction operation to target video picture can be sectional drawing to the target video picture and preserve operation,
Or the mode for directly replicating the target video picture frame and preserving is extracted to complete picture.The extraction conditions
It can be configured based on related informations such as time, Drawing Object or image parameters.
Wherein specifically, the extraction conditions can be configured according to the time.The detection target video figure
Whether piece meets preset extraction conditions, including：Obtain time letter of the target video picture in processing
Breath；Judge whether temporal information of the target video picture in processing is met in preset extraction conditions
Persond eixis；If so, then the target video picture meets preset extraction conditions.
Specifically, persond eixis can be set in extraction conditions, when the persond eixis can be a series of
Between be worth, when the reproduction time or recording time corresponding to the detected target video picture reach these
Between be worth, i.e., triggering extract operation, for example, set 1 second, 10 seconds, the time value of 200 seconds, then, such as
The reproduction time or recording time that really described target video picture is currently located are in 1 second, 10 seconds, 200 seconds
Any one when, think to meet extraction conditions, it is necessary to extract the target video picture.
It is of course also possible to which a temporal information on time interval can be set in extraction conditions, working as
Reproduction time or recording time corresponding to preceding detected target video picture reach that time interval institute is right
During the time answered, i.e. operation is extracted in triggering.For example, time interval is 20 seconds, then, if the target
When the reproduction time or recording time that video pictures are currently located are the time value such as 20 seconds, 40 seconds or 60 seconds,
Think to meet extraction conditions, it is necessary to extract the target video picture.
The extraction conditions can be in picture Drawing Object configured.The detection target video figure
Whether piece meets preset extraction conditions, including：Obtain the Drawing Object that the target video picture includes
Information；Judge whether to include in the Drawing Object described by each Drawing Object information for detecting one or
The description that multiple Drawing Objects meet Drawing Object in the extraction conditions is indicated；If so, then the target is regarded
Frequency picture meets preset extraction conditions.
Specifically, the Drawing Object information can be the type of Drawing Object, meet in the extraction conditions
The description of Drawing Object indicates to refer to：It is right in the type and extraction conditions of Drawing Object in target video picture
Type required by Drawing Object is identical.The type of Drawing Object can specifically include：Personage, animal, plant
Thing or various weather, chronometer phenomenon etc., figure pair can be determined by image recognition technology from picture
The type of elephant.Specifically for example：Identify there is pair of personage in target video picture according to human body recognition technology
As when, that is, meet extraction conditions and extract the target video picture, or identified according to image recognition technology
When the target video picture includes the object of the moon, that is, meet extraction conditions and extract the target video picture.
The Drawing Object information can also be face information or include the face information of special expression, meet
The description of Drawing Object indicates to refer in the extraction conditions：Target video picture includes facial image, or
The expression for the facial image that person includes is identical with the expression required in extraction conditions.Recognition of face skill can be passed through
Art identifies one or more face in target video picture, and mouth, eyes in face characteristic
Expression is determined Deng the feature at position.For example, can clearly detect in the target video image face or
When person clearly detects that face is in the state laughed at, that is, meet extraction conditions and extract the target video picture.
The Drawing Object information can also be graphic object type information and quantity information, meet the extraction
The description of Drawing Object indicates to refer in condition：The type of Drawing Object in target video picture is with extracting bar
And quantity identical to the type required by Drawing Object reaches requirement of the extraction conditions to quantity in part.For example,
When the type of the Drawing Object in target video picture is personage, animal, and total quantity reaches extraction conditions
In requirement on quantity when, that is, meet extraction conditions and extract the target video picture.
The Drawing Object information can also be location object information and/or disaster object information, meet described in carry
The description of Drawing Object in condition is taken to indicate to refer to：Place in target video picture is specific sight spot or position
Put, or target video picture includes thinking that close picture is special with the picture feature such as floods, fire, earthquake
When levying, that is, meet extraction conditions and extract the target video picture.Described specific sight spot or position, it is general can
With by image characteristics extraction, and by with preset sight spot picture feature, position picture feature and urgent
The picture feature of the plurality of pictures such as situation picture feature is for example on fire, flood, earthquake is compared to determine whether
Meet extraction conditions.
In the extraction conditions of Drawing Object, can also according to the development of the real needs and technology of product, after
The related Drawing Object of continuous increase carrys out configuration extraction condition, for example, scene Recognition (mainly passes through 3D modeling
Analysis obtain), key mark identification, such as special logo, car plate, similar Quick Response Code positioning mark, even
Match somebody with somebody in word (these are also to be obtained by image procossing, if also needing to OCR technique if word)
Extraction conditions are put, to extract corresponding video pictures from video.
The extraction conditions can also be configured according to the related image parameters of picture.The detection target is regarded
Whether frequency picture meets preset extraction conditions, including：Obtain the image parameters of the target video picture；
Judge whether the image parameters of the target video picture meet the need in preset extraction conditions to image parameters
Ask instruction；If so, then the target video picture meets preset extraction conditions.The image parameters include：
The parameters such as the luminous flux parameter that the Target Photo is detected when shooting.Luminous flux parameter can be based on shooting
When filming apparatus in sensor sensing obtain, and then judge luminous flux parameter occurrence whether higher than extraction
Threshold value in condition on the parameter setting, if so, then extracting picture, target is determined based on luminous flux parameter
Whether video pictures meet the process that extraction conditions are used primarily in video capture recording.Luminous flux can pass through figure
The brightness processed of picture determines luminous flux parameter.
The embodiment of the present invention can be for video pictures come preset extraction conditions, and then are based on condition come automatic true
The fixed a certain frame video pictures whether extracted in the video recorded or the video recorded, reduce user
What video pictures were obtained is manually operated, and the broadcasting or recording of current video will not be interrupted because of interception picture,
Preferably meet that user extracts to video pictures automate, intelligent demand.
Fig. 2 is referred to again, is a kind of flow signal of image processing method for video of the embodiment of the present invention
Scheme, the methods described of the embodiment of the present invention can be realized by the intelligent terminal that can shoot and/or play video,
It is specifically as follows the terminals such as the smart mobile phone with camera function, tablet personal computer, intelligent wearable device, specifically
, methods described includes：
S201：Set extraction conditions.User can be set manually as needed, specifically can from the time,
Set in terms of Drawing Object or light intensity parameter.Specifically, for example, the 1st for playing or recording can be set
Second, the 10th second, the 200th second equi-time point are used as extraction conditions to extract picture.Or for example, can be arranged on
Express one's feelings and extract picture as extraction conditions for laugh, sobbing, smile etc., extraction conditions can be included existing
The various expressions that all human facial expression recognition functions can be recognized.Or for example, the luminous flux in video increases suddenly
Plus as extraction conditions extract picture, so design be in order to photographed environmental factor be mutated when photo, for example,
Camera is directed at the scene of a suddenly change, and such as light is opened, sunrise scene, can be touched without user
Hair, system oneself can catch moment, the significant photo of extraction comparison.Extraction conditions can also be according to it
The situation of his environmental factor change is set, for example, when occurring multiple faces in video pictures and being detected
Extract picture.
S202：Receive frame of video, and the video photographed according to default extraction conditions, detection current time
The corresponding target video picture of frame.
If reading video file, then video file is decoded, parse each frame video and obtain
Target video picture to be detected；If processing video recording in real time, then directly recorded from picture recording module
Frame of video obtain target video picture to be detected.
S203：According to testing result, determine whether the target video picture meets default extraction conditions.
If so, then performing following S204, if not up to condition, terminates, the target video picture is not extracted.
S204：Sent to user and extract prompt message, the extraction prompt message includes：Auditory tone cues information,
Or icon prompt message；Wherein, the icon prompt message includes：Figure is sent by the icon of preset size
Piece extracts prompt message, and the preset size is less than the size of the Target Photo.If receiving response
Instruction is extracted in the confirmation that the extraction prompt message is sent, then performs following S205.
S205：Target video picture is automatically extracted when reaching default extraction conditions, and stores the target of extraction
Video pictures.
Because video playout speed is very fast, when detecting the target video picture and meeting extraction conditions, institute
S204 is stated while extraction prompt message is sent, the target video picture can be marked, be then prompted to
User, once operation is extracted in the confirmation for detecting user feedback, then carries the target video picture of mark
Take and preserve.
It is alternatively possible to set a minimum extraction conditions so that software will necessarily extract and preserve at least one
Picture.The minimum extraction conditions are similar with the condition setting of step 1, for example, by a period, example
Such as larger than 2 seconds, or face is detected, just extract a photo.
The photo of extraction is stored in local storage, user can as needed at any time carry out review wait grasp
Make, the operation such as can also enter edlin, share.When receiving to regarding corresponding to the target video picture
When quickly checking operation of frequency, is set to thumbnail by the picture for the corresponding video extraction preserved and shows
Show to user, i.e., can also using these photos as the video thumbnail, for pointing out user this section of video
Main contents.
The embodiment of the present invention can be for video pictures come preset extraction conditions, and then are based on condition come automatic true
The fixed a certain frame video pictures whether extracted in the video recorded or the video recorded, reduce user
What video pictures were obtained is manually operated, and the broadcasting or recording of current video will not be interrupted because of interception picture,
And it can preferably meet user couple based on the extraction conditions that time, Drawing Object and image parameter are set
The demand of required picture, preferably meet that user extracts to video pictures automate, intelligent demand.
A kind of picture processing device for video of the embodiment of the present invention is described in detail below.
Fig. 3 is referred to, is a kind of structural representation of picture processing device for video of the embodiment of the present invention
Figure, the described device of the embodiment of the present invention can be arranged on the intelligent terminal that can shoot and/or play video
Realize, be specifically as follows the terminals such as the smart mobile phone with camera function, tablet personal computer, intelligent wearable device,
Specifically, described device includes：
Detection module 1, for detecting whether target video picture meets preset extraction conditions, the target is regarded
Frequency picture includes：The video for having been taken obtaining is clapped in the picture of current time playback process or in video
Current time shoots the picture of processing during taking the photograph；
Extraction module 2, if for meeting preset extraction conditions, extracting the target video picture；Wherein,
Meeting preset extraction conditions includes：The related information extracted for the target video picture meets preset
Extraction conditions.
Extraction operation of the extraction module 2 to target video picture can be that the target video picture is cut
Scheme and preserve operation, or the mode for directly replicating the target video picture frame and preserving is extracted to complete picture.
The extraction conditions can be configured based on related informations such as time, Drawing Object or image parameters.
Specifically alternatively, the related information includes：The Drawing Object letter that the target video picture includes
Breath；The detection module 1, specifically for obtaining the Drawing Object information that the target video picture includes；
Judge whether include one or more figure in the Drawing Object described by each Drawing Object information detected
The description that shape object meets Drawing Object in the extraction conditions is indicated；If so, the then target video picture
Meet preset extraction conditions.
Persond eixis can be set in extraction conditions, and the persond eixis can be a series of time value, when
The reproduction time or recording time that the detection module 1 detects corresponding to the target video picture reach this
A little time values, that is, trigger the extraction module 2 and perform extraction operation.It can also be set in the extraction conditions
Time interval indicates that the detection module 1 carries out detection judgement with specific reference to time interval.
Wherein alternatively, the related information includes：Temporal information of the target video picture in processing,
Specifically include playback process duration information or shoot handling duration information；The detection module 1, specifically for obtaining
Take temporal information of the target video picture in processing；Judge the target video picture processing when
Whether temporal information meets the persond eixis in preset extraction conditions；If so, the then target video picture
Meet preset extraction conditions.
The Drawing Object includes some users and wishes the object that includes in picture, for example, head portrait, possessing
Certain face expressed one's feelings, various types of animals etc. object.Playing or be recorded to the target video figure
During picture, the mode that the detection module 1 can quickly move through picture feature extraction judges the target video figure
Whether it is included in the Drawing Object configured in extraction conditions as in, is extracted if then triggering the extraction module 2
The picture.Signature analysis is carried out to the image in the target video image for example, working as, it is determined that including
When having the face Drawing Object of " smile ", then condition is met, triggering the extraction of extraction module 2, this includes
The target video image of " smile " face Drawing Object.
Wherein alternatively, the related information includes：The image parameters of the target video picture；The inspection
Module 1 is surveyed, the image parameters specifically for obtaining the target video picture；Judge the target video picture
Image parameters whether meet in preset extraction conditions the demands of image parameters indicated；If so, then described
Target video picture meets preset extraction conditions.The image parameters include：The Target Photo is being shot
When the parameter such as the luminous flux parameter that detects.The detection module 1 can be based in filming apparatus when shooting
Sensor sensing obtains luminous flux parameter, and then judges whether the occurrence of luminous flux parameter is higher than extraction conditions
In threshold value on the parameter setting, if so, then triggering the extraction module 2 extracts picture.Luminous flux is joined
Number determines whether target video picture meets the process that extraction conditions are used primarily in video capture recording.
Still optionally further, as shown in figure 3, described device can also include：
Reminding module 3, prompt message is extracted for being sent to user, and the extraction prompt message includes：Sound
Prompt message, or icon prompt message；Wherein, the icon prompt message includes：Pass through preset size
Icon sends picture and extracts prompt message, and the preset size is less than the size of the Target Photo.
Specifically, detected in the detection module 1 after the target video picture meets extraction conditions, can
The prompting for whether extracting picture is issued the user with by the reminding module 3 with elder generation, if so, row extracts described again
Target video picture.Because video playout speed is very fast, extraction is met detecting the target video picture
During condition, the reminding module 3 can mark the target video picture, then be prompted to user, once
Operation is extracted in the confirmation for detecting user feedback, then the target video picture of mark is extracted and preserved i.e.
Can.
Still optionally further, described device can also include：Display module 4, is received to the mesh for working as
When quickly checking operation of video corresponding to mark video pictures, will preserve as the corresponding video extraction
Picture be set to thumbnail and be shown to user.
The photo of extraction is stored in local storage, user can as needed at any time carry out review wait grasp
Make, the operation such as can also enter edlin, share.The display module 4, which is worked as, to be received to the target video
When quickly checking operation of video corresponding to picture, by the picture for the corresponding video extraction preserved
Be set to thumbnail and be shown to user, i.e., can also using these photos as the video thumbnail, for carrying
Show the main contents of this section of video of user.
The embodiment of the present invention can be for video pictures come preset extraction conditions, and then are based on condition come automatic true
The fixed a certain frame video pictures whether extracted in the video recorded or the video recorded, reduce user
What video pictures were obtained is manually operated, and the broadcasting or recording of current video will not be interrupted because of interception picture,
And it can preferably meet user couple based on the extraction conditions that time, Drawing Object and image parameter are set
The demand of required picture, preferably meet that user extracts to video pictures automate, intelligent demand.
Fig. 4 is referred to again, is a kind of structural representation of intelligent terminal of the embodiment of the present invention, and the present invention is implemented
The intelligent terminal of example can be shot for bands such as smart mobile phone, tablet personal computer, intelligent wearable devices and/or
The terminal of video playback capability, can specifically include the structures such as power supply, housing, assortment of keys, communication interface,
In embodiments of the present invention, the intelligent terminal also includes：User interface 100, processor 200 and storage
Device 300, is connected between user interface 100, processor 200 and memory 300 by bus 400.Institute
It can be keyboard, touch-screen etc. to state user interface 100, and be stored with application program in the memory 300,
The processor 200 completes to be directed to video by calling the application program that the memory 300 is stored
Image processing function.
Specifically, by calling the application program stored in the memory 300, the processor 200 is used
Preset extraction conditions whether are met in detection target video picture, the target video picture includes：
Shoot obtained picture of the video in current time playback process or the current time during video capture
Shoot the picture of processing；If meeting preset extraction conditions, the target video picture is extracted；Wherein,
Meeting preset extraction conditions includes：The related information extracted for the target video picture meets preset
Extraction conditions.
Still optionally further, the related information includes：The Drawing Object that the target video picture includes
Information；The processor 200, specifically for obtaining the Drawing Object information that the target video picture includes；
Judge whether include one or more figure in the Drawing Object described by each Drawing Object information detected
The description that shape object meets Drawing Object in the extraction conditions is indicated；If so, the then target video picture
Meet preset extraction conditions.
Still optionally further, the related information includes：Time letter of the target video picture in processing
Breath, specifically includes playback process duration information or shoots handling duration information, the processor 200 is specific to use
Temporal information when the target video picture is obtained in processing；Judge the target video picture in processing
When temporal information whether meet persond eixis in preset extraction conditions；If so, the then target video
Picture meets preset extraction conditions.
Still optionally further, the related information includes：The image parameters of the target video picture, it is described
Processor 200, the image parameters specifically for obtaining the target video picture；Judge the target video figure
Whether the image parameters of piece, which are met in preset extraction conditions, indicates the demand of image parameters；If so, then institute
State target video picture and meet preset extraction conditions.Wherein alternatively, the image parameters include：It is described
The luminous flux parameter that Target Photo is detected when shooting.
Still optionally further, the processor 200, is additionally operable to it is determined that the target video picture meets preset
Extraction conditions after, to user send extract prompt message, in order to receiving response it is described extract prompting
When instruction is extracted in the confirmation of information, the target video picture is extracted, the extraction prompt message includes：Sound
Sound prompt message, or icon prompt message；Wherein, the icon prompt message includes：Pass through preset size
Icon send picture extract prompt message, the preset size be less than the Target Photo size, figure
Mark prompt message can be shown to user by the touch display screen as user interface 100, and be touched by this
Touch the confirmation contact action that display screen receives user.
Still optionally further, the processor 200, it is right to the target video picture when receiving to be additionally operable to
When quickly checking operation of the video answered, contracting is set to by the picture for the corresponding video extraction preserved
Sketch map is shown to user.
Implementing for processor 200 described in the embodiment of the present invention refers to phase in the above method embodiment
Close implementing for step.
The embodiment of the present invention can be for video pictures come preset extraction conditions, and then are based on condition come automatic true
The fixed a certain frame video pictures whether extracted in the video recorded or the video recorded, reduce user
What video pictures were obtained is manually operated, and the broadcasting or recording of current video will not be interrupted because of interception picture,
And it can preferably meet user couple based on the extraction conditions that time, Drawing Object and image parameter are set
The demand of required picture, preferably meet that user extracts to video pictures automate, intelligent demand.
One of ordinary skill in the art will appreciate that all or part of flow in above-described embodiment method is realized,
It can be by computer program to instruct the hardware of correlation to complete, described program can be stored in a calculating
In machine read/write memory medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.
Wherein, described storage medium can for magnetic disc, CD, read-only memory (Read-Only Memory,
) or random access memory (Random Access Memory, RAM) etc. ROM.
Above disclosed is only a kind of preferred embodiment of the invention, can not limit this hair with this certainly
Bright interest field, one of ordinary skill in the art will appreciate that realizing all or part of stream of above-described embodiment
Journey, and the equivalent variations made according to the claims in the present invention, still fall within and invent covered scope.
Claims (13)
1. a kind of image processing method for video, it is characterised in that including：
Whether detection target video picture meets preset extraction conditions, and the target video picture includes：
Through shooting obtained video in the picture of current time playback process or when during video capture currently
Carve the picture for shooting processing；
If meeting preset extraction conditions, the target video picture is extracted；
Wherein, meeting preset extraction conditions includes：The related information extracted for the target video picture
Meet preset extraction conditions.
2. the method as described in claim 1, it is characterised in that the related information includes：The target
The Drawing Object information that video pictures include；Whether the detection target video picture meets preset extraction
Condition, including：
Obtain the Drawing Object information that the target video picture includes；
Judge whether include one in the Drawing Object described by each Drawing Object information detected or many
The description that individual Drawing Object meets Drawing Object in the extraction conditions is indicated；
If so, then the target video picture meets preset extraction conditions.
3. the method as described in claim 1, it is characterised in that the related information includes：The target
Temporal information of the video pictures in processing, specifically includes playback process duration information or shoots handling duration letter
Breath；Whether the detection target video picture meets preset extraction conditions, including：
Obtain temporal information of the target video picture in processing；
Judge whether temporal information of the target video picture in processing is met in preset extraction conditions
Persond eixis；
If so, then the target video picture meets preset extraction conditions.
4. the method as described in claim 1, it is characterised in that the related information includes：The target
Whether the image parameters of video pictures, the detection target video picture meets preset extraction conditions, including：
Obtain the image parameters of the target video picture；
Judge whether the image parameters of the target video picture are met in preset extraction conditions to image parameters
Demand indicate；
If so, then the target video picture meets preset extraction conditions.
5. method as claimed in claim 4, it is characterised in that the image parameters include：The target
The luminous flux parameter that picture is detected when shooting.
6. the method as described in any one of Claims 1-4, it is characterised in that extract the mesh described
Before mark video pictures, in addition to：
Sent to user and extract prompt message, the extraction prompt message includes：Auditory tone cues information, or figure
Mark prompt message；Wherein, the icon prompt message includes：Picture is sent by the icon of preset size to carry
Prompt message is taken, the preset size is less than the size of the Target Photo.
7. the method as described in any one of Claims 1-4, in addition to：
The video corresponding to the target video picture when quickly checking operation, will have been preserved when receiving
The picture for the corresponding video extraction be set to thumbnail and be shown to user.
8. a kind of picture processing device for video, it is characterised in that including：
Detection module, for detecting whether target video picture meets preset extraction conditions, the target is regarded
Frequency picture includes：The video for having been taken obtaining is clapped in the picture of current time playback process or in video
Current time shoots the picture of processing during taking the photograph；
Extraction module, if for meeting preset extraction conditions, extracting the target video picture；Wherein,
Meeting preset extraction conditions includes：The related information extracted for the target video picture meets preset
Extraction conditions.
9. device as claimed in claim 8, it is characterised in that the related information includes：The target
The Drawing Object information that video pictures include；
The detection module, specifically for obtaining the Drawing Object information that the target video picture includes；
Judge whether include one or more figure in the Drawing Object described by each Drawing Object information detected
The description that shape object meets Drawing Object in the extraction conditions is indicated；If so, the then target video picture
Meet preset extraction conditions.
10. device as claimed in claim 8, it is characterised in that the related information includes：The mesh
Temporal information of the video pictures in processing is marked, playback process duration information is specifically included or shoots handling duration
Information；
The detection module, specifically for obtaining temporal information of the target video picture in processing；Sentence
The time whether temporal information of the target video picture in processing of breaking is met in preset extraction conditions refers to
Show；If so, then the target video picture meets preset extraction conditions.
11. device as claimed in claim 8, it is characterised in that the related information includes：The mesh
Mark the image parameters of video pictures；
The detection module, the image parameters specifically for obtaining the target video picture；Judge the mesh
Whether the image parameters of mark video pictures, which are met in preset extraction conditions, indicates the demand of image parameters；If
It is that then the target video picture meets preset extraction conditions.
12. the device as described in any one of claim 8 to 11, it is characterised in that also include：
Reminding module, prompt message is extracted for being sent to user, and the extraction prompt message includes：Sound
Prompt message, or icon prompt message；Wherein, the icon prompt message includes：Pass through preset size
Icon sends picture and extracts prompt message, and the preset size is less than the size of the Target Photo.
13. the device as described in any one of claim 8 to 11, it is characterised in that also include：
Display module, behaviour is checked for working as to receive to the quick of the video corresponding to the target video picture
When making, the picture for the corresponding video extraction preserved is set to thumbnail and is shown to user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610040289.9A CN106991362A (en) | 2016-01-21 | 2016-01-21 | A kind of image processing method and device for video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610040289.9A CN106991362A (en) | 2016-01-21 | 2016-01-21 | A kind of image processing method and device for video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106991362A true CN106991362A (en) | 2017-07-28 |
Family
ID=59413534
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610040289.9A Pending CN106991362A (en) | 2016-01-21 | 2016-01-21 | A kind of image processing method and device for video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106991362A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578024A (en) * | 2017-09-15 | 2018-01-12 | 赵立峰 | A kind of face identification system |
| CN112468867A (en) * | 2020-11-26 | 2021-03-09 | 京东方科技集团股份有限公司 | Video data processing method, processing device, electronic equipment and storage medium |
| CN112712675A (en) * | 2021-01-11 | 2021-04-27 | 深圳创维－Rgb电子有限公司 | Earthquake early warning method, device, system and computer readable storage medium |
| CN113297891A (en) * | 2020-11-13 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Video information processing method and device and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101527690A (en) * | 2009-04-13 | 2009-09-09 | 腾讯科技（北京）有限公司 | Method for intercepting dynamic image, system and device thereof |
| CN103747177A (en) * | 2013-12-31 | 2014-04-23 | 华为技术有限公司 | Method and device for processing video shooting |
| CN103873916A (en) * | 2012-12-13 | 2014-06-18 | 深圳市快播科技有限公司 | Video thumbnail processing method, video thumbnail processing system and video player |
| CN104540004A (en) * | 2015-01-27 | 2015-04-22 | 深圳市中兴移动通信有限公司 | Video screenshot method and video screenshot device |
| CN104883583A (en) * | 2015-06-05 | 2015-09-02 | 广东欧珀移动通信有限公司 | Method and device for acquiring online video screenshot |
| CN104980677A (en) * | 2014-04-02 | 2015-10-14 | 联想(北京)有限公司 | Method and device for adding label into video |
| CN104995639A (en) * | 2013-10-30 | 2015-10-21 | 宇龙计算机通信科技(深圳)有限公司 | Terminal and method for managing video file |
-
2016
- 2016-01-21 CN CN201610040289.9A patent/CN106991362A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101527690A (en) * | 2009-04-13 | 2009-09-09 | 腾讯科技（北京）有限公司 | Method for intercepting dynamic image, system and device thereof |
| CN103873916A (en) * | 2012-12-13 | 2014-06-18 | 深圳市快播科技有限公司 | Video thumbnail processing method, video thumbnail processing system and video player |
| CN104995639A (en) * | 2013-10-30 | 2015-10-21 | 宇龙计算机通信科技(深圳)有限公司 | Terminal and method for managing video file |
| CN103747177A (en) * | 2013-12-31 | 2014-04-23 | 华为技术有限公司 | Method and device for processing video shooting |
| CN104980677A (en) * | 2014-04-02 | 2015-10-14 | 联想(北京)有限公司 | Method and device for adding label into video |
| CN104540004A (en) * | 2015-01-27 | 2015-04-22 | 深圳市中兴移动通信有限公司 | Video screenshot method and video screenshot device |
| CN104883583A (en) * | 2015-06-05 | 2015-09-02 | 广东欧珀移动通信有限公司 | Method and device for acquiring online video screenshot |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578024A (en) * | 2017-09-15 | 2018-01-12 | 赵立峰 | A kind of face identification system |
| CN113297891A (en) * | 2020-11-13 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Video information processing method and device and electronic equipment |
| CN112468867A (en) * | 2020-11-26 | 2021-03-09 | 京东方科技集团股份有限公司 | Video data processing method, processing device, electronic equipment and storage medium |
| CN112712675A (en) * | 2021-01-11 | 2021-04-27 | 深圳创维－Rgb电子有限公司 | Earthquake early warning method, device, system and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3195601B1 (en) | Method of providing visual sound image and electronic device implementing the same | |
| CN101262561B (en) | Imaging apparatus and control method thereof | |
| CN108229369A (en) | Image capturing method, device, storage medium and electronic equipment | |
| CN105809174B (en) | Identify the method and device of image | |
| CN106991362A (en) | A kind of image processing method and device for video | |
| CN109660728B (en) | Photographing method and device | |
| CN108632536B (en) | Camera control method and device, terminal and storage medium | |
| CN109151642B (en) | Intelligent earphone, intelligent earphone processing method, electronic device and storage medium | |
| EP3062513B1 (en) | Video apparatus and photography method thereof | |
| CN111279684A (en) | Shooting control method and electronic device | |
| CN112822388B (en) | Shooting mode triggering method, device, equipment and storage medium | |
| CN109257649B (en) | Multimedia file generation method and terminal equipment | |
| CN104104767B (en) | The treating method and apparatus of associated person information in portable intelligent terminal | |
| CN112597886A (en) | Ride fare evasion detection method and device, electronic equipment and storage medium | |
| CN110019897B (en) | Method and device for displaying picture | |
| CN107710731A (en) | Camera device and image processing method | |
| CN104869283B (en) | A kind of image pickup method and electronic equipment | |
| CN103763454A (en) | Mobile terminal shooting method and device and mobile terminal | |
| CN114495395A (en) | Human shape detection method, monitoring and early warning method, device and system | |
| CN109376674A (en) | Method for detecting human face, device and storage medium | |
| CN104902055B (en) | Contact person's creation method and device | |
| CN106250426A (en) | A kind of photo processing method and terminal | |
| CN113259734B (en) | Intelligent broadcasting guide method, device, terminal and storage medium for interactive scene | |
| CN113766130B (en) | Video shooting method, electronic equipment and device | |
| CN111770279B (en) | Shooting method and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170728 |
|
| RJ01 | Rejection of invention patent application after publication |