CN109815840A - A kind of method and device of determining identification information - Google Patents
A kind of method and device of determining identification information Download PDFInfo
- Publication number
- CN109815840A CN109815840A CN201811641258.4A CN201811641258A CN109815840A CN 109815840 A CN109815840 A CN 109815840A CN 201811641258 A CN201811641258 A CN 201811641258A CN 109815840 A CN109815840 A CN 109815840A
- Authority
- CN
- China
- Prior art keywords
- image
- image information
- face object
- frame
- information
- 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
Landscapes
- Image Processing (AREA)
Abstract
The embodiment of the present application provides a kind of method and device of determining identification information, is related to technical field of video processing, this method comprises: obtaining the video to be processed that monitoring device is shot within a preset period of time, the video to be processed includes N frame image；N is more than or equal to 2；For the first face object, the corresponding image information set of the first face object, the corresponding frame image of each image information are searched from the N frame image；The first face object is any face object that any frame image includes；Feature extraction is carried out to each image information in the image information set of the first face object, obtains the corresponding feature vector of each image information；According to the corresponding feature vector of each image information, the corresponding identification information of the first face object is determined.N frame image is represented by the identification information to be filed or inquired, and compared with prior art, reduces calculation amount, while improving efficiency.
Description
Technical field
The present embodiments relate to technical field of video processing more particularly to a kind of methods and dress of determining identification information
It sets.
Background technique
In today's society, for the needs of safeguard management, it is various public that monitoring device has been covered with street, community, building etc.
Occasion.When alert occurs, the image of suspect or suspected vehicles is first determined from the video data that monitoring device acquires, so
Suspect or suspected vehicles are tracked down and arrested according to the image of suspect or suspected vehicles by police afterwards.
In the prior art, monitoring device acquisition video flowing after, mostly use to every frame image in video flowing carry out detection and
Identification, determines the objects such as face or the vehicle in every frame image, then again matches the object detected in each frame image,
Determine all images an of object, this method is imitated due to needing to be detected and identified that calculation amount is larger to every frame image
Rate is low.
Summary of the invention
Due in the prior art, when determining the image of same target from video flowing, every frame image being detected and being known
Not, it and needs to be detected and identified that calculation amount is larger and efficiency is lower for all information of every frame image, be asked based on above-mentioned
Topic, the embodiment of the present application provide a kind of method and device of determining identification information.
On the one hand, the embodiment of the present application provides a kind of method of determining identification information, this method comprises:
The video to be processed that monitoring device is shot within a preset period of time is obtained, the video to be processed includes N frame
Image；N is more than or equal to 2；
For the first face object, the corresponding image information sets of the first face object are searched from the N frame image
It closes, the corresponding frame image of each image information；The first face object is any face object that any frame image includes；
Feature extraction is carried out to each image information in the image information set of the first face object, obtains each figure
As the corresponding feature vector of information；
According to the corresponding feature vector of each image information, the corresponding identification information of the first face object is determined.
Optionally, described to be directed to the first face object, the image of the first face object is searched from the N frame image
Information, comprising:
For the first image, if the first image is detection frame image, Face datection is carried out to the first image,
Determine the corresponding detection image information of each face object in the first image；If the first image is prediction frame image,
According to the corresponding image information of each face object in the second image, predict that each face object is right in the first image
The forecast image information answered；The first image is any of described N frame image, and second image is first figure
As adjacent image and have determined that or predict the corresponding image information of face object；
Each image information in the image information set to the first face object carries out feature extraction, packet
It includes:
The forecast image information row of detection image information and the first face object to the first face object is special
Sign is extracted.
Optionally, each image information progress feature in the image information set to the first face object mentions
Before taking, further includes:
It determines whether each image information in the image information set of the first face object meets and pushes away frame strategy, institute
It states and pushes away what frame strategy was at least determined according to the picture quality of described image information.
Optionally, whether each image information in the image information set of the determination the first face object meets
Push away frame strategy, comprising:
For the first image information, the ratio of number of frames is pushed away according to the number and the maximum that have pushed away frame image information, really
Fixed first parameter value；The frame image information that pushed away is to be located at the first image information by shooting time before and meet to push away frame
The image information of strategy；The first image information is any one image in the image information set of the first face object
Information；
The second parameter value is determined according to the picture quality of the first image information；
Output parameter is determined according to first parameter value and second parameter value；
Determine whether the first image information is full according to the setup parameter of the output parameter and the output policy
Foot pushes away frame strategy.
On the one hand, the embodiment of the present application provides a kind of device of determining identification information, comprising:
Acquiring unit obtains the video to be processed that monitoring device is shot within a preset period of time, the view to be processed
Frequency includes N frame image；N is more than or equal to 2；
Identification information determination unit searches first face for being directed to the first face object from the N frame image
The corresponding image information set of object, the corresponding frame image of each image information；The first face object is any frame image
Any face object for including；Feature is carried out to each image information in the image information set of the first face object to mention
It takes, obtains the corresponding feature vector of each image information；According to the corresponding feature vector of each image information, first face is determined
The corresponding identification information of object.
Optionally, the identification information determination unit is specifically used for:
For the first image, if the first image is detection frame image, Face datection is carried out to the first image,
Determine the corresponding detection image information of each face object in the first image；If the first image is prediction frame image,
According to the corresponding image information of each face object in the second image, predict that each face object is right in the first image
The forecast image information answered；The first image is any of described N frame image, and second image is first figure
As adjacent image and have determined that or predict the corresponding image information of face object；
The forecast image information row of detection image information and the first face object to the first face object is special
Sign is extracted.
Optionally, the identification information determination unit is also used to:
It determines whether each image information in the image information set of the first face object meets and pushes away frame strategy, institute
It states and pushes away what frame strategy was at least determined according to the picture quality of described image information.
Optionally, the identification information determination unit is specifically used for:
For the first image information, the ratio of number of frames is pushed away according to the number and the maximum that have pushed away frame image information, really
Fixed first parameter value；The frame image information that pushed away is to be located at the first image information by shooting time before and meet to push away frame
The image information of strategy；The first image information is any one image in the image information set of the first face object
Information；
The second parameter value is determined according to the picture quality of the first image information；
Output parameter is determined according to first parameter value and second parameter value；
Determine whether the first image information is full according to the setup parameter of the output parameter and the output policy
Foot pushes away frame strategy.
On the one hand, the embodiment of the present application provides a kind of equipment of determining identification information, including at least one processing unit,
And at least one storage unit, wherein the storage unit is stored with computer program, when described program is single by the processing
When member executes, so that the step of processing unit executes the method for determining identification information.
On the one hand, the embodiment of the present application provides a kind of computer-readable medium, and being stored with can be by determining identification information
Equipment execute computer program, when described program is run in the equipment for determine identification information so that the determination to
The equipment for identifying object executes the step of method for determining identification information.
In the embodiment of the present application, by the way that N frame image to be determined to the face object of every frame image, and it is corresponding to face object
Image carries out feature extraction, obtains the feature vector of the every frame image of N frame image, and N frame has been determined according to all feature vectors
The identification information of image represents N frame image by the identification information and is filed or inquired, and compared with prior art, reduces
Calculation amount, while improving efficiency.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is the system architecture diagram that the embodiment of the present application is applicable in；
Fig. 2 is a kind of flow diagram of the method for determining identification information provided by the embodiments of the present application；
Fig. 3 is a kind of schematic diagram of determining identification information provided by the embodiments of the present application；
Fig. 4 is a kind of flow diagram for determining whether satisfaction and pushing away frame strategy provided by the embodiments of the present application；
Fig. 5 is a kind of structural schematic diagram of the device of determining identification information of the embodiment of the present application；
Fig. 6 is a kind of structural schematic diagram of the equipment of determining identification information of the embodiment of the present application.
Specific embodiment
In order to which the purpose of the present invention, technical solution and beneficial effect is more clearly understood, below in conjunction with attached drawing and implementation
Example, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used to explain this hair
It is bright, it is not intended to limit the present invention.
The method of determination identification information in the embodiment of the present application can be applied to image filing, for example set using monitoring
When the video flowing of standby acquisition is filed, it can be determined in video flowing using the method for identification information determining in the embodiment of the present application
Face frame of the same face in every frame images to be recognized, then determines identification information according to the image information of multiple face frames,
The corresponding face archives of the face are determined according to identification information.
Fig. 1 illustrates the applicable system architecture of the embodiment of the present application, includes monitoring device in the system architecture
101, server 102.Acquisition video flowing takes monitoring device 101 then by the video stream of acquisition to server 102 in real time
It is engaged in including the device for determining object to be identified in device 102, server 102 obtains images to be recognized from video flowing, then determines
The corresponding image-region of object to be identified in images to be recognized.Monitoring device 101 is connected by wireless network and server 102
It connects, monitoring device is the electronic equipment, such as camera, video camera, video recorder etc. for having acquisition image function.Server 102
It is the server cluster or cloud computing center of a server or several servers composition.
Based on system architecture shown in FIG. 1, the embodiment of the present application provides the process of a kind of method of determining identification information,
The process of this method can be executed by determining the device of identification information, determine that the device of identification information can be clothes shown in FIG. 1
Business device 102, as shown in Figure 2, comprising the following steps:
Step 201, the video to be processed that monitoring device is shot within a preset period of time, the video to be processed are obtained
Including N frame image；N is more than or equal to 2；
Monitoring device acquires video flowing in real time, and video flowing is made of multiframe images to be recognized.
Step 202, for the first face object, the corresponding figure of the first face object is searched from the N frame image
As information aggregate, the corresponding frame image of each image information；The first face object is any people that any frame image includes
Face object；
In the embodiment of the present invention, in every frame image include multiple face objects, such as face object 1, face object 2 and
Face object 3 determines the corresponding image information intersection of the face for each face from N frame image, i.e., in above-mentioned example,
An image collection can be determined for face object 1, include the figure of face object 1 in each image in the image collection
As information.
Optionally, in embodiments of the present invention, for the first image of any frame in N frame image, if the first image is inspection
Frame image is surveyed, then Face datection is carried out to the first image, determines the corresponding detection image information of each face object in the first image；
If the first image is to predict that frame image predicts each face according to the corresponding image information of each face object in the second image
Object corresponding forecast image information in the first image；First image is any of N frame image, and the second image is first
The adjacent image of image and have determined that or predict the corresponding image information of face object.
That is, if the first image is that detection frame image is identified from the first image according to Face datection algorithm
Facial image 1, facial image 2 and the corresponding image information of facial image 3, when getting the second image, and the second image is
The next frame image of first image, and when the second image is prediction frame image, for the first face object in the first image,
The forecast image region that similarity is greater than preset threshold is searched in second image, as the first face object in the second image
In corresponding image information；First face object is any face in the first image.
Illustratively, setting in one section of video flowing includes 10 frame images, is by first frame image and the 5th frame image tagged
Detection frame image, the second frame image to the 4th frame image tagged are prediction frame image, and the 6th frame to the tenth frame flag is prediction frame
Image.
Optionally, in embodiments of the present invention, by determining key point in detection frame and predicting the key point in frame
Position, determine prediction frame in object to be identified.
Specifically, key point is the key point of object for identification, for example the key point of face is eyes, face feature
Deng.
Optionally, each face object can be predicted pre- first according to the corresponding image-region of face object each in detection frame
Corresponding image-region in frame is surveyed, and then can predict image letter of each face object in prediction frame in correspondence image region
Breath, i.e., each face object corresponding image information in prediction frame.
Specifically, it for the corresponding image-region of any face object in detection frame, determines and is somebody's turn to do from prediction frame
The similarity of the corresponding image-region of face object is greater than the image-region of preset threshold, as the face object in prediction frame
Corresponding forecast image region.
For example, the corresponding frames images of each face object in known detection frame are set, for face object A in detection frame
Corresponding frames images determine the image for being greater than preset threshold with the similarity of the frames images to face object A from prediction frame
Frame, as the frames images to face object A in prediction frame.
Optionally, in embodiments of the present invention, when obtaining third image, the previous frame of third image is to pass through detection frame
It determines the prediction frame to face object, is then searched in third image by the key point on the prediction frame and prediction frame similar
Degree is greater than the forecast image region of the preset threshold.
In the embodiment of the present invention, any frame image in the video to be processed of monitoring device acquisition is input to classification mould
In type, by disaggregated model, type and the identification object that can obtain the more identification objects having in the frame image are corresponding
Image information；In embodiments of the present invention, the type for identifying object includes pedestrian, non-motor vehicle and motor vehicle, so at this
In inventive embodiments, for a frame image, if including the type of every kind of identification object in the frame image, which is inputted
To classifier, can determine to include pedestrian, non-motor vehicle and motor vehicle in the frame image, and be capable of determining that for each
Identify the identification region of object.
In step 203, feature extraction is carried out to the image collection of each face object, obtains feature vector, the present invention
Feature extraction in embodiment refers to being converted to image information into vector information, and vector information is for characterizing the image information
Illustratively PCA (Principal Component Analysis, principal component analysis) can be used by facial image in feature
Data higher dimensional space is mapped to bottom dimension space, forms feature vector.
In step 203, feature extraction is carried out to each image in image collection, the image in image collection includes logical
Cross the human face image information and the facial image speculated in frame determined by detection frame that Face datection obtains.
In step 204, by the corresponding all feature vectors of any face, determine that the face is corresponding for carrying out
The identification information of identification or filing.
Illustratively, as shown in figure 3, being directed to the first face object, it is determined that it include 4 frame images in image information set,
Feature extraction is carried out by every frame image, it is determined that four feature vectors pass through four vectors, it is determined that the first face object
Identification information.
Optionally, in embodiments of the present invention, identification information can be determined by average weighted method, for example, to upper
Different weights is arranged in the four frame images stated in embodiment, is then weighted and averaged according to the corresponding feature vector of four frame images
Determine the corresponding identification information of four frame images.
It optionally, in embodiments of the present invention, to four frame images setting weight is determined according to the quality of four frame images,
Picture quality is higher, and the weight of setting is higher.
In embodiments of the present invention, feature is carried out to each image information in the image information set of the first face object
Before extraction, it is also necessary to determine whether each image information meets and push away frame strategy, push away frame strategy at least according to image information
What picture quality determined.
It needs to export every frame image in the prior art, and calculation amount is larger to be identified to every frame, in the present invention
In embodiment, introducing pushes away frame strategy, will meet the image for pushing away frame strategy and releases, reduces the calculation amount of identification and filing.
In embodiments of the present invention, in the video to be processed of an object to be identified, the frame of push is more, the knowledge of demand
Other module calculation amount is bigger；And due to obtaining frame image to be pushed away and determining whether frame image to be pushed away can export and export progress
The processing of identification or filing is streaming, so the interval for pushing away frame is bigger, the delay of alarm is bigger；In video to be processed
Face quality is unstable, if it is big to push away frame period, it is meant that can be selected from more frames, the frame quality selected can be more
Good, opposite recognition performance can be higher.
Optionally, it determines whether each image information in the image information set of the first face object meets and pushes away frame plan
Slightly, specifically:
For the first image information, according to the number for having pushed away frame image information and the maximum ratio for pushing away number of frames, the is determined
One parameter value；Having pushed away frame image information is before being located at the first image information by shooting time and to meet the image letter for pushing away frame strategy
Breath；First image information is any one image information in the image information set of the first face object；
The second parameter value is determined according to the picture quality of the first image information；
Output parameter is determined according to the first parameter value and the second parameter value；
It determines whether the first image information meets according to the setup parameter of output parameter and output policy and pushes away frame strategy.
Embodiment in order to preferably explain the present invention describes the embodiment of the present application below with reference to specific implement scene and provides
A kind of determining identification image method, as shown in figure 4, currently having pushed away the quantity of frame image in frame queue wait push away and being
UpdateFrame, the frame number that the last time pushes away frame is lastupdatedFrameID, pushes away interframe and is divided into updateinterval, most
Pushing away number of frames greatly is maxupdateFrame, is specifically included:
Step 401, a new frame image is being obtained in frame queue wait push away, a new frame image frameID, the image is prison
The frame image in the video to be processed of equipment shooting is controlled, video to be processed is used to characterize the rail of a period of time of a pedestrian
Mark；
Step 402, judge whether the picture quality of present frame is better than wait push away all figures in frame queue in addition to present frame
As the picture quality of frame, if so, 403 are thened follow the steps, otherwise, return step 401；
Step 403, judge whether present frame is detection frame in video to be processed, if so, thening follow the steps 404, otherwise
Execute step 405；
Step 404, present frame is exported, and by updateFrame=updateFrame+1；
LastupdatedFrameID=frameID；
Step 405, judge whether present frame is last frame image in video to be processed, if so, thening follow the steps
404, it is no to then follow the steps 406；
Step 406, judge whether updateFrame is more than or equal to maxupdateFrame, if so, return step 401,
It is no to then follow the steps 407；
Step 407, judge whether updateFrame is more than or equal to maxupdateFrame/2, if it is not, thening follow the steps
408, it is no to then follow the steps 409；
Step 408, it determines updateinterval=0, executes step 410；
Step 409, it determines updateinterval=maxinterval, that is, is set as maximum and pushes away frame period；
Step 410, whether the picture quality for judging present frame is high quality graphic, if so, thening follow the steps 411, otherwise
Execute step 412；
Step 411, it determines updateinterval=updateinterval+0.5*maxinterval, executes step
413；
Step 412, whether the picture quality for judging present frame is mean quality image, if so, 414 are thened follow the steps, it is no
Then follow the steps 415；
Step 413, judge whether updateinterval is less than or equal to frameID-lastupdatedframeID, if
It is to then follow the steps 404, it is no to then follow the steps 401；
Step 414, it determines updateinterval=updateinterval+maxinterval, executes step 413；
Step 415, it determines updateinterval=updateinterval+2*maxinterval, executes step 413.
Based on the same technical idea, the embodiment of the invention provides a kind of devices of determining object to be identified, such as Fig. 5 institute
Show, which includes:
Acquiring unit 501 obtains the video to be processed that monitoring device is shot within a preset period of time, described to be processed
Video includes N frame image；N is more than or equal to 2；
Identification information determination unit 502 searches described first from the N frame image for being directed to the first face object
The corresponding image information set of face object, the corresponding frame image of each image information；The first face object is any frame
Any face object that image includes；Each image information in the image information set of the first face object is carried out special
Sign is extracted, and the corresponding feature vector of each image information is obtained；According to the corresponding feature vector of each image information, described first is determined
The corresponding identification information of face object.
Optionally, the identification information determination unit 502 is specifically used for:
For the first image, if the first image is detection frame image, Face datection is carried out to the first image,
Determine the corresponding detection image information of each face object in the first image；If the first image is prediction frame image,
According to the corresponding image information of each face object in the second image, predict that each face object is right in the first image
The forecast image information answered；The first image is any of described N frame image, and second image is first figure
As adjacent image and have determined that or predict the corresponding image information of face object；
The forecast image information row of detection image information and the first face object to the first face object is special
Sign is extracted.
Optionally the identification information determination unit 502 is also used to:
It determines whether each image information in the image information set of the first face object meets and pushes away frame strategy, institute
It states and pushes away what frame strategy was at least determined according to the picture quality of described image information.
Optionally, the identification information determination unit 502 is specifically used for:
For the first image information, the ratio of number of frames is pushed away according to the number and the maximum that have pushed away frame image information, really
Fixed first parameter value；The frame image information that pushed away is to be located at the first image information by shooting time before and meet to push away frame
The image information of strategy；The first image information is any one image in the image information set of the first face object
Information；
The second parameter value is determined according to the picture quality of the first image information；
Output parameter is determined according to first parameter value and second parameter value；
Determine whether the first image information is full according to the setup parameter of the output parameter and the output policy
Foot pushes away frame strategy.
Based on the same technical idea, the embodiment of the present application provides a kind of equipment of determining identification information, such as Fig. 6 institute
Show, including at least one processor 601, and the memory 602 being connect at least one processor, in the embodiment of the present application not
The specific connection medium between processor 601 and memory 602 is limited, is passed through between processor 601 and memory 602 in Fig. 6
For bus connection.Bus can be divided into address bus, data/address bus, control bus etc..
In the embodiment of the present application, memory 602 is stored with the instruction that can be executed by least one processor 601, at least
The instruction that one processor 601 is stored by executing memory 602, can execute and be wrapped in the method for aforementioned determining identification information
The step of including.
Wherein, processor 601 is the control centre of the equipment of determining identification information, can use various interfaces and route connects
The various pieces for connecing the equipment of determining identification information, by running or executing the instruction and calling that are stored in memory 602
The data being stored in memory 602, so that it is determined that identification information.Optionally, processor 601 may include one or more processing
Unit, processor 601 can integrate application processor and modem processor, wherein the main processing operation system of application processor
System, user interface and application program etc., modem processor mainly handles wireless communication.It is understood that above-mentioned modulation
Demodulation processor can not also be integrated into processor 601.In some embodiments, processor 601 and memory 602 can be
It is realized on same chip, in some embodiments, they can also be realized respectively on independent chip.
Processor 601 can be general processor, such as central processing unit (CPU), digital signal processor, dedicated integrated
Circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array or other can
Perhaps transistor logic, discrete hardware components may be implemented or execute the application implementation for programmed logic device, discrete gate
Each method, step and logic diagram disclosed in example.General processor can be microprocessor or any conventional processor
Deng.The step of method in conjunction with disclosed in the embodiment of the present application, can be embodied directly in hardware processor and execute completion, Huo Zheyong
Hardware and software module combination in processor execute completion.
Memory 602 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module.Memory 602 may include the storage medium of at least one type,
It such as may include flash memory, hard disk, multimedia card, card-type memory, random access storage device (Random Access
Memory, RAM), static random-access memory (Static Random Access Memory, SRAM), may be programmed read-only deposit
Reservoir (Programmable Read Only Memory, PROM), read-only memory (Read Only Memory, ROM), band
Electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory,
EEPROM), magnetic storage, disk, CD etc..Memory 602 can be used for carrying or storing have instruction or data
The desired program code of structure type and can by any other medium of computer access, but not limited to this.The application is real
Applying the memory 602 in example can also be circuit or other devices that arbitrarily can be realized store function, for storing program
Instruction and/or data.
Based on the same inventive concept, the embodiment of the present application provides a kind of computer-readable medium, and being stored with can be by true
The computer program that the equipment of identification information executes is determined, when program is run in the equipment for determine identification information, so that determining
The equipment of identification information executes the step of method for determining identification information.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the present invention
Form.It is deposited moreover, the present invention can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of method of determining identification information characterized by comprising
The video to be processed that monitoring device is shot within a preset period of time is obtained, the video to be processed includes N frame image；
N is more than or equal to 2；
For the first face object, the corresponding image information set of the first face object is searched from the N frame image, often
The corresponding frame image of a image information；The first face object is any face object that any frame image includes；
Feature extraction is carried out to each image information in the image information set of the first face object, obtains each image letter
Cease corresponding feature vector；
According to the corresponding feature vector of each image information, the corresponding identification information of the first face object is determined.
2. the method according to claim 1, wherein described be directed to the first face object, from the N frame image
Search the image information of the first face object, comprising:
For the first image, if the first image is detection frame image, Face datection is carried out to the first image, is determined
The corresponding detection image information of each face object in the first image；If the first image is prediction frame image, basis
The corresponding image information of each face object in second image predicts that each face object is corresponding in the first image
Forecast image information；The first image is any of described N frame image, and second image is the first image phase
Adjacent image and have determined that or predict the corresponding image information of face object；
Each image information in the image information set to the first face object carries out feature extraction, comprising:
The forecast image information row feature of detection image information and the first face object to the first face object mentions
It takes.
3. the method according to claim 1, wherein the image information set to the first face object
In each image information carry out feature extraction before, further includes:
It determines whether each image information in the image information set of the first face object meets and pushes away frame strategy, it is described to push away
Frame strategy is at least determining according to the picture quality of described image information.
4. according to the method described in claim 3, it is characterized in that, the image information sets of the determination the first face object
Whether each image information in conjunction, which meets, pushes away frame strategy, comprising:
For the first image information, the ratio of number of frames is pushed away according to the number and the maximum that have pushed away frame image information, determines
One parameter value；The frame image information that pushed away is to be located at the first image information by shooting time before and meet to push away frame strategy
Image information；The first image information is any one image letter in the image information set of the first face object
Breath；
The second parameter value is determined according to the picture quality of the first image information；
Output parameter is determined according to first parameter value and second parameter value；
It determines whether the first image information meets according to the setup parameter of the output parameter and the output policy to push away
Frame strategy.
5. a kind of device of determining identification information characterized by comprising
Acquiring unit obtains the video to be processed that monitoring device is shot within a preset period of time, the video bag to be processed
Include N frame image；N is more than or equal to 2；
Identification information determination unit searches the first face object for being directed to the first face object from the N frame image
Corresponding image information set, the corresponding frame image of each image information；The first face object is that any frame image includes
Any face object；Feature extraction is carried out to each image information in the image information set of the first face object,
Obtain the corresponding feature vector of each image information；According to the corresponding feature vector of each image information, first face pair is determined
As corresponding identification information.
6. device as claimed in claim 5, which is characterized in that the identification information determination unit is specifically used for:
For the first image, if the first image is detection frame image, Face datection is carried out to the first image, is determined
The corresponding detection image information of each face object in the first image；If the first image is prediction frame image, basis
The corresponding image information of each face object in second image predicts that each face object is corresponding in the first image
Forecast image information；The first image is any of described N frame image, and second image is the first image phase
Adjacent image and have determined that or predict the corresponding image information of face object；
The forecast image information row feature of detection image information and the first face object to the first face object mentions
It takes.
7. device as claimed in claim 5, which is characterized in that the identification information determination unit is also used to:
It determines whether each image information in the image information set of the first face object meets and pushes away frame strategy, it is described to push away
Frame strategy is at least determining according to the picture quality of described image information.
8. device as claimed in claim 7, which is characterized in that the identification information determination unit is specifically used for:
For the first image information, the ratio of number of frames is pushed away according to the number and the maximum that have pushed away frame image information, determines
One parameter value；The frame image information that pushed away is to be located at the first image information by shooting time before and meet to push away frame strategy
Image information；The first image information is any one image letter in the image information set of the first face object
Breath；
The second parameter value is determined according to the picture quality of the first image information；
Output parameter is determined according to first parameter value and second parameter value；
It determines whether the first image information meets according to the setup parameter of the output parameter and the output policy to push away
Frame strategy.
9. a kind of equipment of determining identification information, which is characterized in that including at least one processing unit and at least one storage
Unit, wherein the storage unit is stored with computer program, when described program is executed by the processing unit, so that institute
State the step of processing unit perform claim requires 1~4 any claim the method.
10. a kind of computer-readable medium, which is characterized in that it is stored with the calculating that can be executed by the equipment for determining identification information
Machine program, when described program is run in the equipment for determine identification information, so that the equipment of the determining identification information executes
The step of Claims 1 to 4 any the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811641258.4A CN109815840A (en) | 2018-12-29 | 2018-12-29 | A kind of method and device of determining identification information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811641258.4A CN109815840A (en) | 2018-12-29 | 2018-12-29 | A kind of method and device of determining identification information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109815840A true CN109815840A (en) | 2019-05-28 |
Family
ID=66603084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811641258.4A Pending CN109815840A (en) | 2018-12-29 | 2018-12-29 | A kind of method and device of determining identification information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109815840A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112135190A (en) * | 2020-09-23 | 2020-12-25 | 成都市喜爱科技有限公司 | Video processing method, device, system, server and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030068100A1 (en) * | 2001-07-17 | 2003-04-10 | Covell Michele M. | Automatic selection of a visual image or images from a collection of visual images, based on an evaluation of the quality of the visual images |
| CN106897742A (en) * | 2017-02-21 | 2017-06-27 | 北京市商汤科技开发有限公司 | Method, device and electronic equipment for detecting object in video |
| CN108171207A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Face identification method and device based on video sequence |
| CN108229320A (en) * | 2017-11-29 | 2018-06-29 | 北京市商汤科技开发有限公司 | Select frame method and device, electronic equipment, program and medium |
| CN108875480A (en) * | 2017-08-15 | 2018-11-23 | 北京旷视科技有限公司 | A kind of method for tracing of face characteristic information, apparatus and system |
-
2018
- 2018-12-29 CN CN201811641258.4A patent/CN109815840A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030068100A1 (en) * | 2001-07-17 | 2003-04-10 | Covell Michele M. | Automatic selection of a visual image or images from a collection of visual images, based on an evaluation of the quality of the visual images |
| CN106897742A (en) * | 2017-02-21 | 2017-06-27 | 北京市商汤科技开发有限公司 | Method, device and electronic equipment for detecting object in video |
| CN108875480A (en) * | 2017-08-15 | 2018-11-23 | 北京旷视科技有限公司 | A kind of method for tracing of face characteristic information, apparatus and system |
| CN108229320A (en) * | 2017-11-29 | 2018-06-29 | 北京市商汤科技开发有限公司 | Select frame method and device, electronic equipment, program and medium |
| CN108171207A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Face identification method and device based on video sequence |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112135190A (en) * | 2020-09-23 | 2020-12-25 | 成都市喜爱科技有限公司 | Video processing method, device, system, server and storage medium |
| CN112135190B (en) * | 2020-09-23 | 2022-08-16 | 成都市喜爱科技有限公司 | Video processing method, device, system, server and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110807385B (en) | Target detection method, target detection device, electronic equipment and storage medium | |
| CN109740517A (en) | A kind of method and device of determining object to be identified | |
| CN113420729B (en) | Multi-scale target detection method, model, electronic equipment and application thereof | |
| CN108229335A (en) | It is associated with face identification method and device, electronic equipment, storage medium, program | |
| CN109815842A (en) | A kind of method and device of the attribute information of determining object to be identified | |
| CN109740004A (en) | A kind of archiving method and device | |
| CN109783685A (en) | A kind of querying method and device | |
| CN109325964A (en) | A kind of face tracking methods, device and terminal | |
| CN104573625A (en) | Facial detection | |
| CN109726674A (en) | A kind of face identification method and device | |
| CN109800679A (en) | A kind of method and device of the attribute information of determining object to be identified | |
| CN109800675A (en) | A kind of method and device of the identification image of determining face object | |
| Wang et al. | When pedestrian detection meets nighttime surveillance: A new benchmark | |
| CN109815370A (en) | A kind of archiving method and device | |
| CN109872541A (en) | A kind of information of vehicles analysis method and device | |
| CN113766330A (en) | Method and device for generating recommendation information based on video | |
| CN109800668A (en) | A kind of archiving method and device | |
| CN109857891A (en) | A kind of querying method and device | |
| CN109800318A (en) | A kind of archiving method and device | |
| JP2023176023A (en) | System and method for distributed data analytics | |
| CN109783672A (en) | A kind of archiving method and device | |
| Iyer et al. | Adaptive real time traffic prediction using deep neural networks | |
| CN109783663A (en) | A kind of archiving method and device | |
| CN109815840A (en) | A kind of method and device of determining identification information | |
| CN109783664A (en) | A kind of archiving method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200506 Address after: Room 01 and 02, 1st floor, No. 180 Yizhou Road, Xuhui District, Shanghai Applicant after: SHANGHAI YITU TECHNOLOGY Co.,Ltd. Address before: Room 01 and 02, 1st floor, No. 180 Yizhou Road, Xuhui District, Shanghai Applicant before: SHANGHAI YITU TECHNOLOGY Co.,Ltd. Applicant before: SHENZHEN YITU INFORMATION TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190528 |
|
| RJ01 | Rejection of invention patent application after publication |