CN110032978A - Method and apparatus for handling video - Google Patents
Method and apparatus for handling video Download PDFInfo
- Publication number
- CN110032978A CN110032978A CN201910312420.6A CN201910312420A CN110032978A CN 110032978 A CN110032978 A CN 110032978A CN 201910312420 A CN201910312420 A CN 201910312420A CN 110032978 A CN110032978 A CN 110032978A
- Authority
- CN
- China
- Prior art keywords
- image region
- vehicle image
- vehicle
- candidate
- video frame
- 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
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
Embodiment of the disclosure discloses the method and apparatus for handling video.One specific embodiment of this method includes: to obtain target vehicle video, and target video frame is obtained from target vehicle video；The first vehicle image region is determined from target video frame；Based on target video frame and the first vehicle image region, following processing step is executed: candidate video frame is obtained from target vehicle video；Candidate's vehicle image region is determined from candidate video frame；Determine the registration in candidate vehicle image region and the first vehicle image region；Position of the candidate vehicle image region in candidate video frame is adjusted based on registration, obtains the second vehicle image region；Determine whether target vehicle video includes the video frame being located at after candidate video frame；In response to not including, the first vehicle image region and the second vehicle image region are determined as to the vehicle image region to be processed of target vehicle video.The tracking of more smooth, stable vehicle image may be implemented in the embodiment.
Description
Technical field
Embodiment of the disclosure is related to field of computer technology, more particularly, to handles the method and apparatus of video.
Background technique
People can use camera and shoot to vehicle, obtain automobile video frequency.In practice, in order to which automobile video frequency can
With better display effect, it will usually the vehicle image in automobile video frequency is handled (such as addition special efficacy, adjustment color
Deng), at this point, then needing to determine Vehicle Object from the video frame of automobile video frequency.
Currently, generalling use the method for carrying out vehicle detection to the video frame for the video frame that automobile video frequency includes, come
Determine the vehicle image in the video frame.
Summary of the invention
Embodiment of the disclosure proposes the method and apparatus for handling video.
In a first aspect, embodiment of the disclosure provides a kind of method for handling video, this method comprises: obtaining mesh
Automobile video frequency is marked, and obtains target video frame from target vehicle video；Vehicle image region is determined from target video frame
As the first vehicle image region；Based on target video frame and the first vehicle image region, following processing step is executed: from target
In automobile video frequency obtain candidate video frame, wherein candidate video frame be with target video frame it is adjacent and be located at target video frame it
Video frame afterwards；Candidate's vehicle image region is determined from candidate video frame；Determine candidate vehicle image region and the first vehicle
The registration of image-region；Position of the candidate vehicle image region in candidate video frame is adjusted based on identified registration,
Candidate vehicle image region adjusted is obtained as the second vehicle image region；Determine whether target vehicle video includes being located at
Video frame after candidate video frame；Do not include in response to determination, by the first vehicle image region and the second vehicle image region
It is determined as the vehicle image region to be processed of target vehicle video.
It in some embodiments, include: from candidate video frame from candidate's vehicle image determining in candidate video frame region
Determine for the first vehicle image region amplification after image-region, wherein after amplification image-region include and the first vehicle figure
As the corresponding image-region in region；From determining vehicle image region is used as candidate vehicle image area in image-region after amplification
Domain.
In some embodiments, the position of vehicle image region in the video frame key as included by vehicle image region
The coordinate characterization of point；And position of the candidate vehicle image region in candidate video frame is adjusted based on identified registration,
It includes: based on identified registration, respectively that candidate vehicle image region adjusted, which is obtained, as the second vehicle image region
Weight is distributed for candidate vehicle image region and the first vehicle image region；Based on the weight distributed, to candidate vehicle image
Coordinate corresponding to coordinate corresponding to region and the first vehicle image region is weighted summation process, obtains processing result；
Vehicle image region corresponding to processing result obtained is determined as the second vehicle image region.
In some embodiments, vehicle image region by the vehicle image in encirclement vehicle image region rectangle frame table
Sign.
In some embodiments, this method further include: in response to determining that target vehicle video includes being located at candidate video frame
Video frame later uses the last candidate video frame obtained as target video frame, uses the of the last acquisition
Two vehicle image regions continue to execute processing step as the first vehicle image region.
In some embodiments, this method further include: obtain image to be added；To image to be added and target vehicle video
Vehicle image region to be processed merged, image to be added is added to the vehicle image to be processed of target vehicle video
Region obtains processing rear vehicle video.
In some embodiments, this method further include: processing rear vehicle video obtained is sent to communication connection
User terminal, and control user terminal play out processing rear vehicle video.
Second aspect, embodiment of the disclosure provide a kind of for handling the device of video, which includes: first to obtain
Unit is taken, is configured to obtain target vehicle video, and obtains target video frame from target vehicle video；Region determines single
Member is configured to determine vehicle image region as the first vehicle image region from target video frame；First execution unit, quilt
It is configured to execute following processing step based on target video frame and the first vehicle image region: obtaining from target vehicle video
Candidate video frame, wherein candidate video frame is video frame that is adjacent with target video frame and being located at after target video frame；From
Candidate's vehicle image region is determined in candidate video frame；Determining candidate vehicle image region is overlapped with the first vehicle image region
Degree；Position of the candidate vehicle image region in candidate video frame is adjusted based on identified registration, obtains time adjusted
Select vehicle image region as the second vehicle image region；Determine whether target vehicle video includes being located at after candidate video frame
Video frame；Do not include in response to determination, the first vehicle image region and the second vehicle image region are determined as target vehicle
The vehicle image region to be processed of video.
In some embodiments, the first execution unit is further configured to: being determined from candidate video frame and is directed to first
Image-region after the amplification in vehicle image region, wherein image-region includes corresponding with the first vehicle image region after amplification
Image-region；From determining vehicle image region is used as candidate vehicle image region in image-region after amplification.
In some embodiments, the position of vehicle image region in the video frame key as included by vehicle image region
The coordinate characterization of point；And first execution unit be further configured to: based on identified registration, respectively candidate vehicle
Weight is distributed in image-region and the first vehicle image region；Based on the weight distributed, to corresponding to candidate vehicle image region
Coordinate and the first vehicle image region corresponding to coordinate be weighted summation process, obtain processing result；It will be obtained
Vehicle image region corresponding to processing result is determined as the second vehicle image region.
In some embodiments, vehicle image region by the vehicle image in encirclement vehicle image region rectangle frame table
Sign.
In some embodiments, device further include: the second execution unit is configured in response to determine target vehicle view
Frequency includes the video frame after the candidate video frame, uses the last candidate video frame obtained as target video frame,
Use the last the second vehicle image region obtained as the first vehicle image region, continues to execute processing step.
In some embodiments, device further include: second acquisition unit is configured to obtain image to be added；Image
Integrated unit is configured to merge the vehicle image region to be processed of image to be added and target vehicle video, will
Image to be added is added to the vehicle image region to be processed of target vehicle video, obtains processing rear vehicle video.
In some embodiments, device further include: video transmission unit is configured to processing rear vehicle obtained
Video is sent to the user terminal of communication connection, and control user terminal plays out processing rear vehicle video.
The third aspect, embodiment of the disclosure provide a kind of electronic equipment, comprising: one or more processors；Storage
Device is stored thereon with one or more programs, when one or more programs are executed by one or more processors, so that one
Or the method that multiple processors realize any embodiment in the above-mentioned method for handling video.
Fourth aspect, embodiment of the disclosure provide a kind of computer-readable medium, are stored thereon with computer program,
The program realizes any embodiment in the above-mentioned method for handling video method when being executed by processor.
The method and apparatus for handling video that embodiment of the disclosure provides, by obtaining target vehicle video, with
And target video frame is obtained from target vehicle video, then determine vehicle image region as the first vehicle from target video frame
Image-region is then based on target video frame and the first vehicle image region, executes following processing step: regarding from target vehicle
Candidate video frame is obtained in frequency, wherein candidate video frame is view that is adjacent with target video frame and being located at after target video frame
Frequency frame；Candidate's vehicle image region is determined from candidate video frame；Determine candidate vehicle image region and the first vehicle image area
The registration in domain；Candidate vehicle image region is adjusted based on identified registration, obtains candidate vehicle image area adjusted
Domain is as the second vehicle image region；Determine whether target vehicle video includes the video frame being located at after candidate video frame；It rings
It should not include that the first vehicle image region and the second vehicle image region are determined as the to be processed of target vehicle video in determination
Vehicle image region, thus when detecting vehicle image from automobile video frequency, it can be with reference to the vehicle figure in previous video frame
The position of picture is adjusted the position of the vehicle image in current video frame, with this, can make corresponding to current video frame
The position of vehicle image includes position feature corresponding to previous video frame, and then realizes more smooth, stable vehicle image
Tracking, reduce position be mutated caused by vehicle image region shake, help to improve the vehicle image area in automobile video frequency
The fluency that domain is shown.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the disclosure is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the disclosure can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for handling image of the disclosure；
Fig. 3 is according to an embodiment of the present disclosure for handling the schematic diagram of an application scenarios of the method for image；
Fig. 4 is the flow chart according to another embodiment of the method for handling image of the disclosure；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for handling image of the disclosure；
Fig. 6 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of embodiment of the disclosure.
Specific embodiment
The disclosure is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the disclosure can phase
Mutually combination.The disclosure is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the method for handling video of the disclosure or the implementation of the device for handling video
The exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as video processing class is answered on terminal device 101,102,103
With, web browser applications, searching class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, it can be the various electronic equipments with camera, including but not limited to smart phone, tablet computer, e-book reading
(Moving Picture Experts Group Audio Layer III, dynamic image expert compress mark for device, MP3 player
Quasi- audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert compression
Standard audio level 4) player, pocket computer on knee and desktop computer etc..When terminal device 101,102,103 is
When software, it may be mounted in above-mentioned cited electronic equipment.Its may be implemented into multiple softwares or software module (such as with
To provide the multiple softwares or software module of Distributed Services), single software or software module also may be implemented into.It does not do herein
It is specific to limit.
Server 105 can be to provide the server of various services, such as to the mesh that terminal device 101,102,103 is shot
The video processing service device that mark automobile video frequency is handled.Video processing service device can be to the target vehicle video etc. received
Data carry out the processing such as analyzing, and obtain processing result (such as vehicle image region to be processed of target vehicle video).
It should be noted that can be by terminal device for handling the method for video provided by embodiment of the disclosure
101, it 102,103 executes, can also be executed by server 105, correspondingly, the device for handling video can be set in terminal
In equipment 101,102,103, also it can be set in server 105.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software
It, can also be with to be implemented as multiple softwares or software module (such as providing multiple softwares of Distributed Services or software module)
It is implemented as single software or software module.It is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.In the vehicle image to be processed for obtaining target vehicle video
Used data do not need in the case where long-range obtain during region, and above system framework can not include network,
And only include terminal device or server.
With continued reference to Fig. 2, the process of one embodiment of the method for handling video according to the disclosure is shown
200.The method for being used to handle video, comprising the following steps:
Step 201, target vehicle video is obtained, and obtains target video frame from target vehicle video.
It in the present embodiment, can be with for handling the executing subject (such as server 105 shown in FIG. 1) of the method for video
It is regarded by wired connection mode or radio connection from remotely-or locally acquisition target vehicle video, and from target vehicle
Target video frame is obtained in frequency.Wherein, target vehicle video can be the automobile video frequency to be handled it.Specifically, mesh
Mark automobile video frequency can be to carry out shooting video obtained to vehicle.Target video frame can be the view to be handled it
Frequency frame.It is appreciated that since target vehicle video is to carry out shooting acquisition to vehicle, so the video frame of target vehicle video
Vehicle image corresponding to vehicle including shooting.
Specifically, above-mentioned executing subject can obtain target video frame using various methods from target vehicle video.Example
Such as, above-mentioned executing subject can obtain target video frame by the way of obtaining at random from target vehicle video, alternatively, can also
With by target vehicle video, the highest video frame of clarity is as target video frame.Here, to the acquisition side of target video frame
Formula without limitation, it should be clear that, acquired target video frame be in addition to target vehicle video the last one view
Video frame other than frequency frame.
Step 202, determine vehicle image region as the first vehicle image region from target video frame.
In the present embodiment, based on target video frame obtained in step 201, above-mentioned executing subject can be from target video
Determine vehicle image region as the first vehicle image region in frame.Wherein, vehicle image region is the area for including vehicle image
Domain.
It should be noted that in each embodiment that the disclosure provides, the vehicle image region determined from video frame
(candidate vehicle image region including the first vehicle image region and hereinafter) can highlight in a predetermined manner
In video frame.Here, predetermined mode can be various modes, such as the background color in adjustment vehicle image region；
Increase contour line etc. for vehicle image region.
Specifically, above-mentioned executing subject can determine vehicle image region using various methods from target video frame.Make
For example, above-mentioned executing subject can export target video frame for showing first, then obtain user from target video frame
The image-region selected is as vehicle image region.
As another example, above-mentioned executing subject can carry out vehicle detection to target video frame, and then regard from target
Vehicle image region is determined in frequency frame.In practice, vehicle inspection can be carried out to target video frame based on the principle of Face datection
It surveys.Specifically, available vehicle detection model trained in advance, and then target video frame is inputted into vehicle detection model, it obtains
Obtain vehicle image region.Wherein, vehicle detection model can be using sample vehicle image and for sample vehicle image it is preparatory
Determining sample vehicle image region as training sample, predetermined initial model is trained and the model that obtains.
Here, the initial model for obtaining vehicle detection model for training can be the various models for image procossing, such as convolution
Neural network.
Step 203, it is based on target video frame and the first vehicle image region, executes processing step.
In the present embodiment, based on the first vehicle figure obtained in target video frame obtained in step 201 and step 202
As region, above-mentioned executing subject can execute following processing step (step 2031- step 2036):
Step 2031, candidate video frame is obtained from target vehicle video.
In the present embodiment, candidate video frame is video that is adjacent with target video frame and being located at after target video frame
Frame.Here, the video frame after target video frame is to be arranged in the sequence of frames of video corresponding to target vehicle video
Video frame after target video frame.It is appreciated that target vehicle video is substantially to arrange according to the sequencing of time
Sequence of frames of video.
Step 2032, candidate's vehicle image region is determined from candidate video frame.
In the present embodiment, candidate vehicle image region is region in candidate video frame, including vehicle image.
Specifically, above-mentioned executing subject can determine candidate's vehicle image area using various methods from candidate video frame
Domain.As an example, candidate video frame can be inputted above-mentioned vehicle detection model by above-mentioned executing subject, candidate vehicle image is obtained
Region.
In practice, after obtaining vehicle image region corresponding to target video frame, vehicle image region can be carried out
Tracking, to determine that the vehicle image region in the video frame after target video frame may be implemented with this to target carriage
Vehicle image region corresponding to video is uniformly processed, and improves treatment effeciency.
In some optional implementations of the present embodiment, above-mentioned vehicle image region (including candidate vehicle image area
Domain and the first vehicle image region) above-mentioned use (can be equivalent to by the rectangle frame of the vehicle image in encirclement vehicle image region
In the contour line for highlighting vehicle image region) characterization.
Particularly, above-mentioned rectangle frame can be the minimum rectangle frame of encirclement vehicle image.
Step 2033, the registration in candidate vehicle image region and the first vehicle image region is determined.
Herein, registration can be to be overlapped journey for characterize candidate vehicle image region and the first vehicle image region
The numerical value of degree.Specifically, registration is bigger, the face in candidate vehicle image region Yu the first vehicle image area coincidence can be characterized
Product is bigger.
It should be noted that the registration in candidate vehicle image region and the first vehicle image region is referred to when candidate vehicle
Registration both when image-region and the first vehicle image region are located on the same image.Therefore in the present embodiment, on
Stating executing subject can first be set in candidate vehicle image region and the first vehicle image region in the same image, then
Determine the registration in candidate vehicle image region and the first vehicle image region.
Specifically, candidate vehicle image region can be added in target video frame by above-mentioned executing subject, and then determine
The registration in candidate vehicle image region and the first vehicle image region；Alternatively, above-mentioned executing subject can be by the first vehicle figure
As region is added in candidate video frame, and then determine the registration in candidate vehicle image region and the first vehicle image region；
Alternatively, the above-mentioned available preset initial pictures of executing subject, and by candidate vehicle image region and the first vehicle image area
Domain is added in above-mentioned initial pictures, and then determines the registration in candidate vehicle image region and the first vehicle image region.Its
In, initial pictures are identical as the shape size of the video frame of target vehicle video.
It should be noted that above-mentioned executing subject can adopt adds vehicle image region (packet in the picture in various manners
Include candidate vehicle image region and the first vehicle image region), however, it is desirable to it is clear that, the vehicle image region after addition
Position in new images should be identical as position of the vehicle image region in original image before addition.
Herein, after candidate image area and the first vehicle image region being set in the same image, above-mentioned execution
Main body can determine the area in candidate vehicle image region Yu the first vehicle image area coincidence, and then based on the coincidence determined
Area, determine the registration of candidate image area and the first vehicle image region.Specifically, as an example, can directly by
The area of identified coincidence is determined as registration；Alternatively, the area in candidate vehicle image region can be determined first, then may be used
It carries out asking quotient with the area of area and candidate vehicle image region to identified coincidence, acquisition asks quotient's result as candidate figure
As the registration in region and the first vehicle image region.
Step 2034, position of the candidate vehicle image region in candidate video frame is adjusted based on identified registration,
Candidate vehicle image region adjusted is obtained as the second vehicle image region.
In the present embodiment, based on the registration determined in step 2033, above-mentioned executing subject can use various methods
Position of the candidate vehicle image region in candidate video frame is adjusted, and then candidate vehicle image region adjusted is determined as
Second vehicle image region.It is appreciated that candidate vehicle image region is highlighted image-region in candidate video frame, into
And herein, the position for adjusting candidate vehicle image region is substantially to adjust highlighted image district in candidate video frame
Domain.
Specifically, as an example, vehicle image region by the vehicle image in encirclement vehicle image region rectangle frame table
Sign, then above-mentioned executing subject can determine whether registration is more than or equal to default registration threshold value, default in response to being more than or equal to
Registration threshold value adjusts position of the rectangle frame in candidate video frame corresponding to candidate vehicle image region, so that candidate vehicle
Central point corresponding to the rectangle frame of image-region is overlapped with central point corresponding to the rectangle frame in the first vehicle image region,
And then the candidate vehicle image region for being characterized rectangle frame adjusted is determined as the second vehicle image region.Wherein, rectangle
Central point corresponding to frame can be formed by the central point of rectangle for rectangle frame.
In some optional implementations of the present embodiment, vehicle image region (including the first vehicle image region and
Candidate vehicle image region) position in the video frame can the key point as included by vehicle image region coordinate characterization,
Wherein, the key point in vehicle image region is point crucial in vehicle image region, specifically, can be influence vehicle image area
The point of the position of domain in the video frame, such as can be the central point in vehicle image region, or the wheel for vehicle image region
Point (such as vertex of the rectangle frame for characterizing vehicle image region) on exterior feature etc.；And above-mentioned executing subject can by with
Lower step obtains the second vehicle image region:
Firstly, above-mentioned executing subject can be based on identified registration, respectively candidate vehicle image region and first
Weight is distributed in vehicle image region.
Specifically, above-mentioned executing subject can be based on registration, adopt in various manners as candidate vehicle image region and the
Weight is distributed in one vehicle image region.
As an example, technical staff can pre-establish the corresponding relationship of registration and weight by above-mentioned executing subject
Table.In turn, above-mentioned executing subject can be according to identified registration, according to above-mentioned mapping table, for candidate vehicle image
Weight is distributed in region and the first vehicle image region；Alternatively, above-mentioned executing subject can acquiring technology personnel first preset
The first weight, the second weight and registration threshold value.Wherein, the first weight is greater than the second weight.Then, above-mentioned executing subject can
To determine whether identified registration is greater than registration threshold value.In turn, when identified registration is greater than registration threshold value,
Above-mentioned executing subject can give the first weight distribution to the first vehicle image region, give the second weight distribution to candidate vehicle image
Area coordinate；When identified registration is less than or equal to registration threshold value, above-mentioned executing subject can be by the first weight distribution
To candidate vehicle image region, the second weight distribution is given to the first vehicle image region.
Then, based on the weight distributed, above-mentioned executing subject can be to the seat of the key point in candidate vehicle image region
The coordinate of the key point in mark and the first vehicle image region is weighted summation process, obtains processing result.
Finally, vehicle image region corresponding to processing result obtained can be determined as second by above-mentioned executing subject
Vehicle image region.
Here, vehicle image region corresponding to processing result is using point corresponding to processing result as the vehicle of key point
Image-region.
As an example, key point is the central point in vehicle image region, the coordinate of the key point in candidate vehicle image region
For (12,14), the coordinate of the key point in the first vehicle image region is (15,18), is based on registration, for candidate vehicle image area
The weight that domain and the first vehicle image region are distributed respectively is respectively 0.4,0.6.Then above-mentioned executing subject can be based on weight 0.4
With 0.6, summation process is weighted to coordinate (12,14) and coordinate (15,18), is obtained processing result (13.8,16.4).Into
And the position in the adjustable candidate vehicle image region of above-mentioned executing subject so that the central point in candidate vehicle image region with
Point corresponding to processing result (13.8,16.4) is overlapped, and then obtains the second vehicle image region.
Step 2035, determine whether target vehicle video includes the video frame being located at after candidate video frame.
It step 2036, does not include being determined as the first vehicle image region and the second vehicle image region in response to determination
The vehicle image region to be processed of target vehicle video.
In the present embodiment, vehicle image region to be processed is figure in target vehicle video, to be handled it
As region.
In practice, after obtaining image-region to be processed, above-mentioned executing subject can be carried out vehicle image region to be processed
Various processing, for example, adjusting the color of the pixel in vehicle image region to be processed.
In some optional implementations of the present embodiment, after obtaining vehicle image region to be processed, above-mentioned execution master
Body can execute following steps:
Firstly, the above-mentioned available image to be added of executing subject, wherein image to be added can be for be added to vehicle
Image in image-region.
Specifically, above-mentioned executing subject can be by wired connection mode or radio connection from remotely-or locally obtaining
Image to be added.
Then, above-mentioned executing subject can vehicle image region to be processed to image to be added and target vehicle video into
Image to be added, is added to the vehicle image region to be processed of target vehicle video by row fusion, obtains processing rear vehicle view
Frequently.
Herein, it can be predetermined (example that image to be added, which is added to the position in vehicle image region to be processed,
Such as can be the center of image-region), or pass through what is determined after identifying to vehicle image region to be processed
(such as the image-region of wheel can be identified from vehicle image region to be processed, and then will be where the image-region of wheel
Position be determined as the position for adding image to be added).
In some optional implementations of the present embodiment, after obtaining processing rear vehicle video, above-mentioned executing subject is also
Processing rear vehicle video obtained can be sent to the user terminal of communication connection, and after control user terminal is to processing
Automobile video frequency plays out.Wherein, user terminal is terminal used by a user, with the communication connection of above-mentioned executing subject.Tool
Body, above-mentioned executing subject can send control signal to user terminal, and then control user terminal and carry out to processing rear video
It plays.
Herein, since the vehicle image region in the video frame of processing rear vehicle video is based on the previous of the video frame
What the vehicle image region of a video frame determined, so the vehicle after treatment in automobile video frequency, in two adjacent video frames
The transition of image-region can be more smooth, stable, therefore, when helping to improve playback process rear vehicle video, vehicle image area
The fluency that domain is shown.
In some optional implementations of the present embodiment, above-mentioned executing subject may also respond to determine target vehicle
Video includes the video frame after candidate video frame, uses the last candidate video frame obtained as target video
Frame uses the last the second vehicle image region obtained as the first vehicle image region, continues to execute above-mentioned processing step
Suddenly (step 2031-2036).
With continued reference to the signal that Fig. 3, Fig. 3 are according to the application scenarios of the method for handling video of the present embodiment
Figure.In the application scenarios of Fig. 3, the target vehicle video 302 available first of server 301, and from target vehicle video
First video frame 3021 (target video frame) is obtained in 302.Then, server 301 can be from first video frame 3021
Determine vehicle image region as the first vehicle image region 30211.Then, server 301 can be based on first video frame
3021 and the first vehicle image region 30211, it executes following processing step: obtaining second view from target vehicle video 302
Frequency frame 3022 (candidate video frame)；Candidate's vehicle image region 30221 is determined from second video frame 3022；Determine candidate's vehicle
The registration 303 of image-region 30221 and the first vehicle image region 30211；It is adjusted and is waited based on identified registration 303
Position of the vehicle image region 30221 in second video frame 3022 is selected, candidate vehicle image region adjusted is obtained and makees
For the second vehicle image region 30222；Determine whether target vehicle video 302 includes that third video frame (is located at candidate video
Video frame after frame)；Do not include in response to determination, by the first vehicle image region 30211 and the second vehicle image region
30222 are determined as the vehicle image region 304 to be processed of target vehicle video 302.
The method provided by the above embodiment of the disclosure can refer to previous when detecting vehicle image from automobile video frequency
The position of vehicle image in a video frame is adjusted the position of the vehicle image in current video frame, with this, can make
The position of vehicle image corresponding to current video frame includes position feature corresponding to previous video frame, and then is realized more flat
The tracking of sliding, stable vehicle image reduces the shake in vehicle image region caused by position is mutated, and helps to improve vehicle view
The fluency that vehicle image region in frequency is shown.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method for handling video.The use
In the process 400 of the method for processing video, comprising the following steps:
Step 401, target vehicle video is obtained, and obtains target video frame from target vehicle video.
It in the present embodiment, can be with for handling the executing subject (such as server 105 shown in FIG. 1) of the method for video
It is regarded by wired connection mode or radio connection from remotely-or locally acquisition target vehicle video, and from target vehicle
Target video frame is obtained in frequency.Wherein, target vehicle video is the automobile video frequency to be handled it.Specifically, target carriage
Video can be to carry out vehicle to shoot video obtained.Target video frame can be the video to be handled it
Frame.
Step 402, determine vehicle image region as the first vehicle image region from target video frame.
In the present embodiment, based on target video frame obtained in step 401, above-mentioned executing subject can be from target video
Determine vehicle image region as the first vehicle image region in frame.Wherein, vehicle image region is the area for including vehicle image
Domain.
Step 403, it is based on target video frame and the first vehicle image region, executes following processing step: from target vehicle
Candidate video frame is obtained in video；The image-region after determining the amplification for the first vehicle image region in candidate video frame；
From determining vehicle image region is used as candidate vehicle image region in image-region after amplification；Determine candidate vehicle image region with
The registration in the first vehicle image region；Candidate vehicle image region is adjusted in candidate video frame based on identified registration
Position, obtain candidate vehicle image region adjusted as the second vehicle image region；Whether determine target vehicle video
Including the video frame after candidate video frame；Do not include in response to determination, by the first vehicle image region and the second vehicle
Image-region is determined as the vehicle image region to be processed of target vehicle video.
In the present embodiment, based on the first vehicle figure obtained in target video frame obtained in step 401 and step 402
As region, above-mentioned executing subject can execute following processing step (step 4031- step 4037):
Step 4031, candidate video frame is obtained from target vehicle video.
Step 4032, the image-region after determining the amplification for the first vehicle image region in candidate video frame.
Herein, image-region includes image-region corresponding with the first vehicle image region after amplification, and after amplification
The size of image-region is greater than the first vehicle image region.Wherein, image-region corresponding with the first vehicle image region is
It is identical as the shape in the first vehicle image region, size difference, and the position in candidate video frame and the first vehicle image area
The identical image-region in position of the domain in target video frame.
Specifically, above-mentioned executing subject can be determined first from candidate video frame it is corresponding with the first vehicle image region
Image-region, then identified image-region is amplified, image-region after being amplified.It should be noted that putting
Image-region can be predetermined relative to the amplification factor in the first vehicle image region after big, or random to generate
's.
Step 4033, from determining vehicle image region is used as candidate vehicle image region in image-region after amplification.
Specifically, above-mentioned executing subject can using various methods from after amplification in image-region determine vehicle image region
As candidate vehicle image region.As an example, above-mentioned executing subject can be by image-region input training in advance after amplification
Vehicle detection model obtains vehicle image region as candidate vehicle image region.
Step 4034, the registration in candidate vehicle image region and the first vehicle image region is determined.
Step 4035, position of the candidate vehicle image region in candidate video frame is adjusted based on identified registration,
Candidate vehicle image region adjusted is obtained as the second vehicle image region.
Step 4036, determine whether target vehicle video includes the video frame being located at after candidate video frame.
It step 4037, does not include being determined as the first vehicle image region and the second vehicle image region in response to determination
The vehicle image region to be processed of target vehicle video.
Above-mentioned steps 401, step 402, step 4031, step 4034, step 4035, step 4036 and step 4037 can be with
Be respectively adopted in previous embodiment step 201, step 202, step 2031, step 2033, step 2034, step 2035 and
The similar mode of step 2036 executes, above with respect to step 201, step 202, step 2031, step 2033, step 2034, step
Rapid 2035 and the description of step 2036 be also applied for step 401, step 402, step 4031, step 4034, step 4035, step
4036 and step 4037, details are not described herein again.
Figure 4, it is seen that the method for handling video compared with the corresponding embodiment of Fig. 2, in the present embodiment
Process 400 highlight from candidate video frame determine for the first vehicle image region amplification after image-region, then from
The step of vehicle image region is as candidate vehicle image region is determined after amplification in image-region.It is appreciated that adjacent two
The change in location in the vehicle image region in a video frame is little, so, the present embodiment can determine needle from candidate video frame
Vehicle image is detected after amplification, as a result, in turn to image-region after the amplification in the first vehicle image region in image-region
The scheme of the present embodiment description can reduce detection range, detection efficiency be improved, and it is possible to reduce for determining the second vehicle
The consumption of the process resource of image-region, and then help to reduce the resource consumption during processing video, improve video processing
Efficiency.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, present disclose provides one kind for handling view
One embodiment of the device of frequency, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 5, the device 500 for handling video of the present embodiment includes: that first acquisition unit 501, region are true
Order member 502 and the first execution unit 503.Wherein, first acquisition unit 501 is configured to obtain target vehicle video, and
Target video frame is obtained from target vehicle video；Area determination unit 502 is configured to determine vehicle from target video frame
Image-region is as the first vehicle image region；First execution unit 503 is configured to based on target video frame and the first vehicle
Image-region executes following processing step: from target vehicle video obtain candidate video frame, wherein candidate video frame be with
Target video frame it is adjacent and be located at target video frame after video frame；Candidate's vehicle image area is determined from candidate video frame
Domain；Determine the registration in candidate vehicle image region and the first vehicle image region；It is adjusted based on identified registration candidate
Position of the vehicle image region in candidate video frame obtains candidate vehicle image region adjusted as the second vehicle image
Region；Determine whether target vehicle video includes the video frame being located at after candidate video frame；Do not include in response to determination, by
One vehicle image region and the second vehicle image region are determined as the vehicle image region to be processed of target vehicle video.
It in the present embodiment, can be by wired connection side for handling the first acquisition unit 501 of the device 500 of video
Formula or radio connection are from remotely-or locally acquisition target vehicle video, and target view is obtained from target vehicle video
Frequency frame.Wherein, target vehicle video is the automobile video frequency to be handled it.Specifically, target vehicle video can be pair
Vehicle carries out shooting video obtained.Target video frame can be the video frame to be handled it.
In the present embodiment, the target video frame obtained based on first acquisition unit 501, area determination unit 502 can be with
Determine vehicle image region as the first vehicle image region from target video frame.Wherein, vehicle image region be include vehicle
The region of image.
In the present embodiment, the target video frame and area determination unit 502 obtained based on first acquisition unit 501 is obtained
The first vehicle image region, the first execution unit 503 can execute following processing step: obtaining and wait from target vehicle video
Select video frame；Candidate's vehicle image region is determined from candidate video frame；Determine candidate vehicle image region and the first vehicle figure
As the registration in region；Position of the candidate vehicle image region in candidate video frame is adjusted based on identified registration, is obtained
Candidate vehicle image region adjusted is obtained as the second vehicle image region；Determine whether target vehicle video includes being located to wait
Select the video frame after video frame；Do not include in response to determination, the first vehicle image region and the second vehicle image region is true
It is set to the vehicle image region to be processed of target vehicle video.
Wherein, candidate video frame is video frame that is adjacent with target video frame and being located at after target video frame.Candidate vehicle
Image-region is region in candidate video frame, including vehicle image.Registration can be for for characterizing candidate vehicle figure
As the numerical value in region and the area of the first vehicle image area coincidence.Specifically, registration is bigger, candidate vehicle figure can be characterized
As region and the area of the first vehicle image area coincidence are bigger.
In some optional implementations of the present embodiment, the first execution unit 503 can be further configured to: from
Image-region after the determining amplification for the first vehicle image region in candidate video frame, wherein image-region includes after amplification
Image-region corresponding with the first vehicle image region；From determining vehicle image region is used as candidate in image-region after amplification
Vehicle image region.
In some optional implementations of the present embodiment, the position of vehicle image region in the video frame is by vehicle figure
The coordinate of the key point as included by region characterizes；And first execution unit 503 can be further configured to: based on institute really
Weight is distributed in fixed registration, respectively candidate vehicle image region and the first vehicle image region；Based on the weight distributed,
Summation process is weighted to coordinate corresponding to coordinate corresponding to candidate vehicle image region and the first vehicle image region,
Obtain processing result；Vehicle image region corresponding to processing result obtained is determined as the second vehicle image region.
In some optional implementations of the present embodiment, vehicle image region is by the vehicle in encirclement vehicle image region
The rectangle frame characterization of image.
In some optional implementations of the present embodiment, device 500 can also include: the second execution unit (in figure
It is not shown), it is configured in response to determine that target vehicle video includes the video frame after candidate video frame, using nearest
The candidate video frame once obtained uses the last the second vehicle image region obtained as first as target video frame
Vehicle image region, continues to execute processing step.
In some optional implementations of the present embodiment, device 500 can also include: second acquisition unit (in figure
It is not shown), it is configured to obtain image to be added；Image fusion unit (not shown) is configured to image to be added
It is merged with the vehicle image region to be processed of target vehicle video, image to be added is added to target vehicle video
Vehicle image region to be processed obtains processing rear vehicle video.
In some optional implementations of the present embodiment, device 500 can also include: video transmission unit (in figure
It is not shown), it is configured to for processing rear vehicle video obtained being sent to the user terminal of communication connection, and control user
Terminal plays out processing rear vehicle video.
It is understood that all units recorded in the device 500 and each step phase in the method with reference to Fig. 2 description
It is corresponding.As a result, above with respect to the operation of method description, the beneficial effect of feature and generation be equally applicable to device 500 and its
In include unit, details are not described herein.
The device provided by the above embodiment 500 of the disclosure can be referred to when detecting vehicle image from automobile video frequency
The position of vehicle image in previous video frame is adjusted the position of the vehicle image in current video frame, can with this
So that the position of vehicle image corresponding to current video frame includes position feature corresponding to previous video frame, and then realize more
For the tracking of smooth, stable vehicle image, reduces the shake in vehicle image region caused by position is mutated, help to improve vehicle
The fluency that vehicle image region in video is shown.
Below with reference to Fig. 6, it illustrates the electronic equipment (end of example as shown in figure 1 for being suitable for being used to realize the embodiment of the present disclosure
End equipment 101,102,103 or server 105) 600 structural schematic diagram.Terminal device in the embodiment of the present disclosure may include
But it is not limited to such as mobile phone, laptop, digit broadcasting receiver, PDA (personal digital assistant), PAD (plate electricity
Brain), PMP (portable media player), the mobile terminal of car-mounted terminal (such as vehicle mounted guidance terminal) etc. and such as
The fixed terminal of digital TV, desktop computer etc..Electronic equipment shown in Fig. 6 is only an example, should not be to the disclosure
The function and use scope of embodiment bring any restrictions.
As shown in fig. 6, electronic equipment 600 may include processing unit (such as central processing unit, graphics processor etc.)
601, random access can be loaded into according to the program being stored in read-only memory (ROM) 602 or from storage device 608
Program in memory (RAM) 603 and execute various movements appropriate and processing.In RAM 603, it is also stored with electronic equipment
Various programs and data needed for 600 operations.Processing unit 601, ROM 602 and RAM603 are connected with each other by bus 604.
Input/output (I/O) interface 605 is also connected to bus 604.
In general, following device can connect to I/O interface 605: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 606 of head, microphone, accelerometer, gyroscope etc.；Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 607 of dynamic device etc.；Storage device 608 including such as tape, hard disk etc.；And communication device 609.Communication device
609, which can permit electronic equipment 600, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 6 shows tool
There is the electronic equipment 600 of various devices, it should be understood that being not required for implementing or having all devices shown.It can be with
Alternatively implement or have more or fewer devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communication device 609, or from storage device 608
It is mounted, or is mounted from ROM 602.When the computer program is executed by processing unit 601, the embodiment of the present disclosure is executed
Method in the above-mentioned function that limits.
It should be noted that computer-readable medium described in the disclosure can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the disclosure, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In open, computer-readable signal media may include in a base band or as the data-signal that carrier wave a part is propagated,
In carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable and deposit
Any computer-readable medium other than storage media, the computer-readable signal media can send, propagate or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: electric wire, optical cable, RF (radio frequency) etc. are above-mentioned
Any appropriate combination.
Above-mentioned computer-readable medium can be included in above-mentioned electronic equipment；It is also possible to individualism, and not
It is fitted into the electronic equipment.Above-mentioned computer-readable medium carries one or more program, when said one or more
When a program is executed by the electronic equipment, so that the electronic equipment: obtaining target vehicle video, and from target vehicle video
Obtain target video frame；Determine vehicle image region as the first vehicle image region from target video frame；It is regarded based on target
Frequency frame and the first vehicle image region, execute following processing step: candidate video frame is obtained from target vehicle video, wherein
Candidate video frame is video frame that is adjacent with target video frame and being located at after target video frame；It is determined from candidate video frame
Candidate vehicle image region；Determine the registration in candidate vehicle image region and the first vehicle image region；Based on identified
Registration adjusts position of the candidate vehicle image region in candidate video frame, obtains candidate vehicle image region adjusted and makees
For the second vehicle image region；Determine whether target vehicle video includes the video frame being located at after candidate video frame；In response to
Determination does not include that the first vehicle image region and the second vehicle image region are determined as to the vehicle to be processed of target vehicle video
Image-region.
The calculating of the operation for executing the disclosure can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present disclosure can be realized by way of software, can also be by hard
The mode of part is realized.Wherein, the title of unit does not constitute the restriction to the unit itself under certain conditions, for example, the
One acquiring unit is also described as " obtaining the unit of target vehicle video and target video frame ".
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that the open scope involved in the disclosure, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from design disclosed above, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed in the disclosure
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (16)
1. a kind of method for handling video, comprising:
Target vehicle video is obtained, and obtains target video frame from the target vehicle video；
Determine vehicle image region as the first vehicle image region from the target video frame；
Based on the target video frame and first vehicle image region, following processing step is executed: from the target vehicle
Candidate video frame is obtained in video, wherein candidate video frame is adjacent with target video frame and is located at after target video frame
Video frame；Candidate's vehicle image region is determined from candidate video frame；Determine candidate vehicle image region and the first vehicle image
The registration in region；Position of the candidate vehicle image region in candidate video frame is adjusted based on identified registration, is obtained
Candidate vehicle image region adjusted is as the second vehicle image region；Determine whether the target vehicle video includes being located at
Video frame after candidate video frame；Do not include in response to determination, by the first vehicle image region and the second vehicle image region
It is determined as the vehicle image region to be processed of the target vehicle video.
2. according to the method described in claim 1, wherein, the candidate vehicle image region determining from candidate video frame is wrapped
It includes:
The image-region after determining the amplification for the first vehicle image region in candidate video frame, wherein image district after amplification
Domain includes image-region corresponding with the first vehicle image region；
From determining vehicle image region is used as candidate vehicle image region in image-region after amplification.
3. according to the method described in claim 1, wherein, the position of vehicle image region in the video frame is by vehicle image region
The coordinate of included key point characterizes；And
It is described that position of the candidate vehicle image region in candidate video frame is adjusted based on identified registration, after being adjusted
Candidate vehicle image region include: as the second vehicle image region
Based on identified registration, weight is distributed in respectively candidate vehicle image region and the first vehicle image region；
Based on the weight distributed, to corresponding to coordinate corresponding to candidate vehicle image region and the first vehicle image region
Coordinate is weighted summation process, obtains processing result；
Vehicle image region corresponding to processing result obtained is determined as the second vehicle image region.
4. according to the method described in claim 1, wherein, vehicle image region is by the vehicle image in encirclement vehicle image region
Rectangle frame characterization.
5. according to the method described in claim 1, wherein, the method also includes:
In response to the video frame that the determination target vehicle video includes after candidate video frame, obtained using the last time
Candidate video frame as target video frame, use the last the second vehicle image region obtained as the first vehicle image
Region continues to execute the processing step.
6. method described in one of -5 according to claim 1, wherein the method also includes:
Obtain image to be added；
The vehicle image region to be processed of the image to be added and the target vehicle video is merged, will it is described to
Addition image is added to the vehicle image region to be processed of the target vehicle video, obtains processing rear vehicle video.
7. according to the method described in claim 6, wherein, the method also includes:
Processing rear vehicle video obtained is sent to the user terminal of communication connection, and the control user terminal to institute
Processing rear vehicle video is stated to play out.
8. a kind of for handling the device of video, comprising:
First acquisition unit is configured to obtain target vehicle video, and target view is obtained from the target vehicle video
Frequency frame；
Area determination unit is configured to determine vehicle image region as the first vehicle image area from the target video frame
Domain；
First execution unit is configured to execute following place based on the target video frame and first vehicle image region
Manage step: from the target vehicle video obtain candidate video frame, wherein candidate video frame be it is adjacent with target video frame,
And it is located at the video frame after target video frame；Candidate's vehicle image region is determined from candidate video frame；Determine candidate's vehicle
The registration of image-region and the first vehicle image region；Candidate vehicle image region is adjusted based on identified registration waiting
The position in video frame is selected, obtains candidate vehicle image region adjusted as the second vehicle image region；Determine the mesh
Whether mark automobile video frequency includes the video frame being located at after candidate video frame；Do not include in response to determination, by the first vehicle image
Region and the second vehicle image region are determined as the vehicle image region to be processed of the target vehicle video.
9. device according to claim 8, wherein first execution unit is further configured to:
The image-region after determining the amplification for the first vehicle image region in candidate video frame, wherein image district after amplification
Domain includes image-region corresponding with the first vehicle image region；
From determining vehicle image region is used as candidate vehicle image region in image-region after amplification.
10. device according to claim 8, wherein the position of vehicle image region in the video frame is by vehicle image area
The coordinate of key point included by domain characterizes；And
First execution unit is further configured to:
Based on identified registration, weight is distributed in respectively candidate vehicle image region and the first vehicle image region；
Based on the weight distributed, to corresponding to coordinate corresponding to candidate vehicle image region and the first vehicle image region
Coordinate is weighted summation process, obtains processing result；
Vehicle image region corresponding to processing result obtained is determined as the second vehicle image region.
11. device according to claim 8, wherein vehicle image region is by the vehicle figure in encirclement vehicle image region
The rectangle frame of picture characterizes.
12. device according to claim 8, wherein described device further include:
Second execution unit is configured in response to determine that the target vehicle video includes the view after candidate video frame
Frequency frame uses the last candidate video frame obtained as target video frame, the second vehicle figure obtained using the last time
Picture region continues to execute the processing step as the first vehicle image region.
13. the device according to one of claim 8-12, wherein described device further include:
Second acquisition unit is configured to obtain image to be added；
Image fusion unit is configured to the vehicle image area to be processed to the image to be added and the target vehicle video
Domain is merged, and the image to be added is added to the vehicle image region to be processed of the target vehicle video, is obtained
Handle rear vehicle video.
14. device according to claim 13, wherein described device further include:
Video transmission unit is configured to for processing rear vehicle video obtained being sent to the user terminal of communication connection, with
And the control user terminal plays out the processing rear vehicle video.
15. a kind of electronic equipment, comprising:
One or more processors；
Storage device is stored thereon with 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 are real
The now method as described in any in claim 1-7.
16. a kind of computer-readable medium, is stored thereon with computer program, wherein the realization when program is executed by processor
Method as described in any in claim 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910312420.6A CN110032978A (en) | 2019-04-18 | 2019-04-18 | Method and apparatus for handling video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910312420.6A CN110032978A (en) | 2019-04-18 | 2019-04-18 | Method and apparatus for handling video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110032978A true CN110032978A (en) | 2019-07-19 |
Family
ID=67238966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910312420.6A Pending CN110032978A (en) | 2019-04-18 | 2019-04-18 | Method and apparatus for handling video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110032978A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111222509A (en) * | 2020-01-17 | 2020-06-02 | 北京字节跳动网络技术有限公司 | Target detection method and device and electronic equipment |
| CN111314626A (en) * | 2020-02-24 | 2020-06-19 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing video |
| CN111666874A (en) * | 2020-06-05 | 2020-09-15 | 上海眼控科技股份有限公司 | Illegal overtaking processing method and device, electronic equipment and readable storage medium |
| CN111695540A (en) * | 2020-06-17 | 2020-09-22 | 北京字节跳动网络技术有限公司 | Video frame identification method, video frame cutting device, electronic equipment and medium |
| CN115661701A (en) * | 2022-10-09 | 2023-01-31 | 中国科学院半导体研究所 | Real-time image processing method and device, electronic equipment and readable storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101393609A (en) * | 2008-09-18 | 2009-03-25 | 北京中星微电子有限公司 | Target detection tracking method and device |
| CN101807303A (en) * | 2010-03-05 | 2010-08-18 | 北京智安邦科技有限公司 | Tracking device based on multiple-target mean shift |
| CN102750527A (en) * | 2012-06-26 | 2012-10-24 | 浙江捷尚视觉科技有限公司 | Long-time stable human face detection and tracking method in bank scene and long-time stable human face detection and tracking device in bank scene |
| CN102982559A (en) * | 2012-11-28 | 2013-03-20 | 大唐移动通信设备有限公司 | Vehicle tracking method and system |
| CN103593856A (en) * | 2013-11-20 | 2014-02-19 | 中国科学院深圳先进技术研究院 | Method and system for tracking single target |
| CN103617412A (en) * | 2013-10-31 | 2014-03-05 | 电子科技大学 | Real-time lane line detection method |
| CN106778484A (en) * | 2016-11-16 | 2017-05-31 | 南宁市浩发科技有限公司 | Moving vehicle tracking under traffic scene |
| CN108154119A (en) * | 2017-12-25 | 2018-06-12 | 北京奇虎科技有限公司 | Automatic Pilot processing method and processing device based on the segmentation of adaptive tracing frame |
| CN109255321A (en) * | 2018-09-03 | 2019-01-22 | 电子科技大学 | A kind of visual pursuit classifier construction method of combination history and instant messages |
-
2019
- 2019-04-18 CN CN201910312420.6A patent/CN110032978A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101393609A (en) * | 2008-09-18 | 2009-03-25 | 北京中星微电子有限公司 | Target detection tracking method and device |
| CN101807303A (en) * | 2010-03-05 | 2010-08-18 | 北京智安邦科技有限公司 | Tracking device based on multiple-target mean shift |
| CN102750527A (en) * | 2012-06-26 | 2012-10-24 | 浙江捷尚视觉科技有限公司 | Long-time stable human face detection and tracking method in bank scene and long-time stable human face detection and tracking device in bank scene |
| CN102982559A (en) * | 2012-11-28 | 2013-03-20 | 大唐移动通信设备有限公司 | Vehicle tracking method and system |
| CN103617412A (en) * | 2013-10-31 | 2014-03-05 | 电子科技大学 | Real-time lane line detection method |
| CN103593856A (en) * | 2013-11-20 | 2014-02-19 | 中国科学院深圳先进技术研究院 | Method and system for tracking single target |
| CN106778484A (en) * | 2016-11-16 | 2017-05-31 | 南宁市浩发科技有限公司 | Moving vehicle tracking under traffic scene |
| CN108154119A (en) * | 2017-12-25 | 2018-06-12 | 北京奇虎科技有限公司 | Automatic Pilot processing method and processing device based on the segmentation of adaptive tracing frame |
| CN109255321A (en) * | 2018-09-03 | 2019-01-22 | 电子科技大学 | A kind of visual pursuit classifier construction method of combination history and instant messages |
Non-Patent Citations (1)
| Title |
|---|
| 陈健等: "《结合椭圆拟合与参数传递的瞳孔检测方法》", 《仪器仪表学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111222509A (en) * | 2020-01-17 | 2020-06-02 | 北京字节跳动网络技术有限公司 | Target detection method and device and electronic equipment |
| CN111222509B (en) * | 2020-01-17 | 2023-08-18 | 北京字节跳动网络技术有限公司 | Target detection method and device and electronic equipment |
| CN111314626A (en) * | 2020-02-24 | 2020-06-19 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing video |
| CN111314626B (en) * | 2020-02-24 | 2021-12-07 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing video |
| CN111666874A (en) * | 2020-06-05 | 2020-09-15 | 上海眼控科技股份有限公司 | Illegal overtaking processing method and device, electronic equipment and readable storage medium |
| CN111695540A (en) * | 2020-06-17 | 2020-09-22 | 北京字节跳动网络技术有限公司 | Video frame identification method, video frame cutting device, electronic equipment and medium |
| CN111695540B (en) * | 2020-06-17 | 2023-05-30 | 北京字节跳动网络技术有限公司 | Video frame identification method, video frame clipping method, video frame identification device, electronic equipment and medium |
| CN115661701A (en) * | 2022-10-09 | 2023-01-31 | 中国科学院半导体研究所 | Real-time image processing method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858445B (en) | Method and apparatus for generating a model | |
| CN110032978A (en) | Method and apparatus for handling video | |
| CN109993150B (en) | Method and device for identifying age | |
| CN109902186A (en) | Method and apparatus for generating neural network | |
| CN108898185A (en) | Method and apparatus for generating image recognition model | |
| CN108492364A (en) | The method and apparatus for generating model for generating image | |
| CN110162670A (en) | Method and apparatus for generating expression packet | |
| CN110059623B (en) | Method and apparatus for generating information | |
| CN109829432A (en) | Method and apparatus for generating information | |
| CN110516678B (en) | Image processing method and device | |
| CN109255337A (en) | Face critical point detection method and apparatus | |
| CN110288625B (en) | Method and apparatus for processing image | |
| CN110213614A (en) | The method and apparatus of key frame are extracted from video file | |
| CN109977839A (en) | Information processing method and device | |
| CN109961141A (en) | Method and apparatus for generating quantization neural network | |
| CN109754464A (en) | Method and apparatus for generating information | |
| WO2021088790A1 (en) | Display style adjustment method and apparatus for target device | |
| CN110111241A (en) | Method and apparatus for generating dynamic image | |
| CN108171167B (en) | Method and apparatus for exporting image | |
| CN110059624A (en) | Method and apparatus for detecting living body | |
| CN111930228A (en) | Method, device, equipment and storage medium for detecting user gesture | |
| CN110223220A (en) | A kind of method and apparatus handling image | |
| CN110619101B (en) | Method and apparatus for processing information | |
| CN111027495A (en) | Method and device for detecting key points of human body | |
| CN110046571A (en) | The method and apparatus at age for identification |
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 |