CN108038473A - Method and apparatus for output information - Google Patents
Method and apparatus for output information Download PDFInfo
- Publication number
- CN108038473A CN108038473A CN201711455262.7A CN201711455262A CN108038473A CN 108038473 A CN108038473 A CN 108038473A CN 201711455262 A CN201711455262 A CN 201711455262A CN 108038473 A CN108038473 A CN 108038473A
- Authority
- CN
- China
- Prior art keywords
- image
- destination object
- identification model
- recognition result
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for output information.One embodiment of this method includes：Obtain image to be detected sequence；For each image in image to be detected sequence, the image is inputted to multiple identification models of training in advance, recognition result corresponding with each identification model respectively is obtained, based on obtained recognition result, determines whether present destination object in the image；The identification information of the target image is included using image in image to be detected sequence, to present the destination object as target image, output.This embodiment improves the flexibility of the identification to destination object.
Description
Technical field
The invention relates to field of computer technology, and in particular to Internet technical field, it is more particularly, to defeated
Go out the method and apparatus of information.
Background technology
Image recognition technology, refers to handle image using computer, analyzed and understood, to identify various different moulds
The target of formula and the technology to picture.General industry using industrial camera in use, shoot picture, and then recycling software is according to figure
Piece ash jump does further identifying processing.Therefore, destination object (such as someone) can be carried out using image recognition technology
Tracking.
Existing mode is typically to carry out recognition of face to image merely with human face recognition model, if recognizing destination object
Face, then can determine to present destination object in image, however, then can not be from institute when destination object is back to camera device
Face is identified in the image of shooting.
The content of the invention
The embodiment of the present application proposes the method and apparatus for output information.
In a first aspect, the embodiment of the present application provides a kind of method for output information, this method includes：Obtain to be checked
Altimetric image sequence；For each image in image to be detected sequence, which is inputted to multiple identifications of training in advance
Model, obtains recognition result corresponding with each identification model respectively, based on obtained recognition result, determine be in the image
It is no to present destination object；Using image in image to be detected sequence, to present destination object as target image, output bag
Identification information containing target image.
In certain embodiments, multiple identification models include human face recognition model and at least one local identification model, people
Face identification model is used to the human face region of destination object be identified, each part at least one part identification model
Identification model is used to a regional area of destination object be identified.
In certain embodiments, for each image in image to be detected sequence, which is inputted to advance instruction
Experienced multiple identification models, obtain recognition result corresponding with each identification model respectively, including：For image to be detected sequence
In each image, which is inputted to human face recognition model, obtains face recognition result, and the image is inputted to each
A part identification model, obtains local recognition result corresponding with each part identification model.
In certain embodiments, based on obtained recognition result, determine destination object whether is presented in the image, wrap
Include：For each image in image to be detected sequence, in response to determining that the corresponding face recognition result instruction of the image should
The human face region of destination object is not presented in image, and local recognition result corresponding with the image indicates that the image is in
The quantity of the regional area of existing destination object is not less than default value, determines that the image presents destination object.
In certain embodiments, based on obtained recognition result, determine destination object whether is presented in the image, wrap
Include：For each image in image to be detected sequence, in response to determining that the corresponding face recognition result instruction of the image should
The human face region of destination object is presented in image, determines that the image presents destination object.
In certain embodiments, based on obtained recognition result, determine destination object whether is presented in the image, wrap
Include：For each image in image to be detected sequence, in response to determining that the corresponding face recognition result instruction of the image should
The human face region of destination object is not presented in image, and local recognition result corresponding with the image indicates that the image is in
The quantity of the regional area of existing destination object is less than default value, determines that the image does not present destination object.
In certain embodiments, at least one local identification model includes at least one of following：Clothes colour recognition model,
Garment identification model, knapsack colour recognition model, knapsack style identification model, hair style identification model, cap identification model,
Glasses identification model, height identification model, build identification model.
Second aspect, the embodiment of the present application provide a kind of device for output information, which includes：Obtain single
Member, is configured to obtain image to be detected sequence；Input unit, is configured to for each figure in image to be detected sequence
Picture, which is inputted to multiple identification models of training in advance, obtains recognition result corresponding with each identification model respectively,
Based on obtained recognition result, determine whether present destination object in the image；Output unit, being configured to will be to be detected
Image in image sequence, presenting destination object includes the identification information of target image as target image, output.
In certain embodiments, multiple identification models include human face recognition model and at least one local identification model, people
Face identification model is used to the human face region of destination object be identified, each part at least one part identification model
Identification model is used to a regional area of destination object be identified.
In certain embodiments, input unit is further configured to：For each figure in image to be detected sequence
Picture, which is inputted to human face recognition model, obtains face recognition result, and the image is inputted to each local identification mould
Type, obtains local recognition result corresponding with each part identification model.
In certain embodiments, input unit is further configured to：For each figure in image to be detected sequence
Picture, in response to determining that the corresponding face recognition result of the image indicates not presenting the human face region of destination object in the image,
And part recognition result corresponding with the image indicates that the quantity of the regional area for the destination object that the image is presented is not small
In default value, determine that the image presents destination object.
In certain embodiments, input unit is further configured to：For each figure in image to be detected sequence
Picture, in response to determining that the corresponding face recognition result of the image indicates to present the human face region of destination object in the image, really
The fixed image presents destination object.
In certain embodiments, input unit is further configured to：For each figure in image to be detected sequence
Picture, in response to determining that the corresponding face recognition result of the image indicates not presenting the human face region of destination object in the image,
And part recognition result corresponding with the image indicates that the quantity of the regional area for the destination object that the image is presented is less than
Default value, determines that the image does not present destination object.
In certain embodiments, at least one local identification model includes at least one of following：Clothes colour recognition model,
Garment identification model, knapsack colour recognition model, knapsack style identification model, hair style identification model, cap identification model,
Glasses identification model, height identification model, build identification model.
The third aspect, the embodiment of the present application provide a kind of server, including：One or more processors；Storage device,
For storing one or more programs, when one or more programs are executed by one or more processors so that one or more
Processor realizes the method as being used for any embodiment in the method for output information.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable recording medium, are stored thereon with computer journey
Sequence, realizes the method as being used for any embodiment in the method for output information when which is executed by processor.
Method and apparatus provided by the embodiments of the present application for output information, by obtaining image to be detected sequence, and
Afterwards for each image in image to be detected sequence, which is inputted to multiple identification models of training in advance, is obtained
Recognition result corresponding with each identification model respectively, and obtained recognition result is based on, determine whether presented in the image
There is destination object, finally included image in image to be detected sequence, to present destination object as target image, output
The identification information of target image, determines whether presented in image so as to the corresponding recognition result of the multiple identification models of synthesis
Destination object, improves the flexibility of the identification to destination object.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that this application can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for output information of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for output information of the application；
Fig. 4 is the structure diagram according to one embodiment of the device for output information of the application；
Fig. 5 is adapted for the structure diagram of the computer system of the electronic equipment for realizing the embodiment of the present application.
Embodiment
The application 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
It illustrate only easy to describe, in attached drawing and invent relevant part with related.
It should be noted that in the case where there is no conflict, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1, which is shown, can apply the method for output information of the application or the example of the device for output information
Sexual system framework 100.
As shown in Figure 1, system architecture 100 can include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted with using terminal equipment 101,102,103 by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as photography and vedio recording class should on terminal device 101,102,103
Applied with, image processing class, searching class application etc..In addition, terminal device 101,102,103 can also be connected with the first-class figure of shooting
As harvester, and obtain the image that image acquisition device arrives.
Terminal device 101,102,103 can be the various electronic equipments for having display screen and supporting network service, bag
Include but be not limited to smart mobile phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 105 can be to provide the server of various services, such as the figure to the upload of terminal device 101,102,103
As the image processing server handled.Image processing server can dock received image to be detected etc. and analyze etc.
Processing, and handling result (such as optimizing image) is fed back into terminal device.
It should be noted that the image generating method that the embodiment of the present application is provided generally is performed by server 105, accordingly
Ground, video generation device are generally positioned in server 105.
It is pointed out that the local of server 105 can also directly store image to be detected, or directly acquire image and adopt
Acquisition means collection image, at this time, server 105 can directly extract local or image collecting device gathered it is to be detected
Image is detected, and at this time, terminal device 101,102,103 and network 104 can be not present in exemplary system architecture 100.
It may also be noted that can also be provided with image processing class application in terminal device 101,102,103, terminal is set
Standby 101,102,103, which can also be based on image processing class, applies to image to be detected progress Face datection, at this time, image generation side
Method can also be performed by terminal device 101,102,103, correspondingly, video generation device can also be arranged at terminal device 101,
102nd, in 103.At this time, server 105 and network 104 can be not present in exemplary system architecture 100.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the flow of one embodiment of the method for output information according to the application is shown
200.The method for output information, comprises the following steps：
Step 201, image to be detected sequence is obtained.
In the present embodiment, the electronic equipment run thereon for the method for output information can obtain image to be detected
Sequence, wherein, above-mentioned image to be detected sequence can include being made of multiple images according to the sequencing of image capturing time
Sequence.In practice, the image in image to be detected sequence can be that the first-class image collecting device of monitoring camera is collected.
Herein, above-mentioned electronic equipment can be connected with image collecting device (such as imaging first-class), and store above-mentioned figure
The image collected as harvester.Above-mentioned electronic equipment can choose the image stored in some period as to be detected
Image, and collect according to shooting time sequencing for image to be detected sequence.At this time, above-mentioned electronic equipment can be directly from this
Ground obtains above-mentioned image to be detected sequence.Above-mentioned image to be detected sequence can be other electricity being connected with above-mentioned electronic equipment
Sub- equipment is sent to above-mentioned electronic equipment by wired connection mode or radio connection.Other above-mentioned electronic equipments can
To be connected with image collecting device, the image that image acquisition device arrives can be obtained.Wherein, above-mentioned radio connection
It can include but is not limited to 3G/4G connections, WiFi connections, bluetooth connection, WiMAX connections, Zigbee connections, UWB (ultra
Wideband) connection and other currently known or exploitation in the future radio connections.
Step 202, for each image in image to be detected sequence, which is inputted to what is trained in advance multiple
Identification model, obtains recognition result corresponding with each identification model respectively, based on obtained recognition result, determines the image
In whether present destination object.
In the present embodiment, for each image in image to be detected sequence, above-mentioned electronic equipment can first by
The image is inputted to multiple identification models of training in advance, obtains recognition result corresponding with each identification model respectively, then,
Obtained recognition result can be based on, determines destination object (such as someone) whether is presented in the image.Wherein, it is above-mentioned
Multiple identification models can be for multiple models being locally identified to destination object, for example, can include to target
Human bioequivalence model that head identification model that the head of object is identified, the body to destination object are identified, to mesh
Clothes identification model that the clothing of mark object is identified, shoes identification model that the shoes of destination object are identified etc.
Deng.Above-mentioned each identification model can utilize machine learning algorithm, based on corresponding training sample to image recognition can be achieved
The model (such as convolutional neural networks (Convolutional Neural Network, CNN)) of function carries out Training
Obtain afterwards.For example, training sample can include the head image of above-mentioned destination object used in above-mentioned head identification model
With the mark for characterizing the head image that the head image is destination object.Above-mentioned convolutional neural networks can include convolution
Layer, pond layer, full articulamentum etc., wherein, convolutional layer can be used for extracting characteristics of image, and pond layer can be used for the letter to input
Breath carries out down-sampled (downsample), and full articulamentum can be used for exporting recognition result.In practice, convolutional neural networks
(Convolutional Neural Network, CNN) is a kind of feedforward neural network, its artificial neuron can respond one
Surrounding cells in partial coverage, have outstanding performance for image procossing, therefore, it is possible to be carried out using convolutional neural networks
Image recognition.
It should be noted that above-mentioned electronic equipment is based on obtained recognition result, sharp can determine in various manners should
Whether destination object is presented in image.As an example, if recognition result instruction identifies and above-mentioned target pair is presented in image
The local quantity of elephant, then can be true not less than default value (such as 3, be respectively the head of destination object, shoes, clothing)
Above-mentioned destination object is presented in the fixed image；If other result instruction identifies the part that above-mentioned destination object is presented in image
Quantity be less than above-mentioned default value, then can determine not presenting above-mentioned destination object in the image.
In some optional implementations of the present embodiment, above-mentioned multiple identification models can include human face recognition model
With at least one local identification model, wherein, above-mentioned human face recognition model can be used for the human face region to above-mentioned destination object
It is identified, each local identification model in above-mentioned at least one local identification model can be used for above-mentioned destination object
A regional area (such as clothes color, garment, knapsack color, knapsack style etc.) be identified.Need what is illustrated
It is that above-mentioned at least one local identification model can include but is not limited at least one of following：Clothes colour recognition model, clothes
Style identification model, knapsack colour recognition model, knapsack style identification model, hair style identification model, cap identification model, glasses
Identification model, height identification model, build identification model.Each part identification model can utilize machine learning algorithm, base
In corresponding training sample to the model (such as convolutional neural networks (Convolutional of image identification function can be achieved
Neural Network, CNN)) carry out Training after obtain.At this time, for every in above-mentioned image to be detected sequence
One image, above-mentioned electronic equipment can determine whether present destination object in the image as follows：It is possible, firstly, to
The image is inputted to above-mentioned human face recognition model, obtains face recognition result；Then, above-mentioned electronic equipment can be by the image
Input obtains local recognition result corresponding with each part identification model to each local identification model.Above-mentioned electronics is set
It is standby to be based on obtained face recognition result and local recognition result, sharp it can determine whether presented in the image in various manners
There is destination object.
In some optional implementations of the present embodiment, above-mentioned electronic equipment is in above-mentioned image to be detected sequence
Each image, in response to determine the corresponding face recognition result of the image indicate not presenting above-mentioned target pair in the image
The human face region of elephant and local recognition result corresponding with the image indicate the office for the above-mentioned destination object that the image is presented
The quantity in portion region is not less than default value (such as 3), it may be determined that the image presents above-mentioned destination object.
In some optional implementations of the present embodiment, above-mentioned electronic equipment is in above-mentioned image to be detected sequence
Each image, in response to determine the corresponding face recognition result of the image indicate to present above-mentioned destination object in the image
Human face region, it may be determined that the image presents above-mentioned destination object.
In some optional implementations of the present embodiment, above-mentioned electronic equipment is in above-mentioned image to be detected sequence
Each image, in response to determine the corresponding face recognition result of the image indicate not presenting above-mentioned target pair in the image
The human face region of elephant, and local recognition result corresponding with the image indicates the office for the above-mentioned destination object that the image is presented
The quantity in portion region is less than default value (such as 3), it may be determined that the image does not present above-mentioned destination object.
Step 203, using image in image to be detected sequence, to present destination object as target image, output bag
Identification information containing target image.
In the present embodiment, above-mentioned electronic equipment can by it is in above-mentioned image to be detected sequence, present destination object
Image as target image, output includes the identification information of target image.It should be noted that above-mentioned identification information can be with
The information such as shooting time, camera site including each target image.In practice, target image that above-mentioned electronic equipment is exported
In the destination object region presented can be identified using highlighted frame.
In some optional implementations of the present embodiment, above-mentioned electronic equipment is also based on each target image
Shooting time, camera site (for example, the image collecting device position of shooting image can be determined as camera site), really
The mobile route of fixed above-mentioned destination object.As an example, the target image in image to be detected sequence is respectively first object figure
Picture, the second target image and the 3rd target image, above-mentioned first object image is 9:00 shooting is simultaneously shot in first position, above-mentioned
Second target image is 9:01 shooting is simultaneously shot in the second place, and above-mentioned 3rd target image is 9:05 shoots and in the third place
Shooting, then the mobile route of above-mentioned destination object can be moved to said second position from above-mentioned first position, then from above-mentioned
The second place is moved to above-mentioned the third place.After the mobile route of above-mentioned destination object is determined, above-mentioned electronic equipment can be with
Output is used for the mobile route information for characterizing above-mentioned mobile route.
With continued reference to Fig. 3, Fig. 3 is a signal according to the application scenarios of the method for output information of the present embodiment
Figure.In the application scenarios of Fig. 3, image processing server can obtain what is be made of the image of monitoring camera collection first
Image to be detected sequence 301, then for each image in image to be detected sequence 301, image processing server can
Recognition result corresponding with each identification model respectively is obtained with multiple identification models based on training in advance, afterwards image procossing
Server can be based on obtained recognition result, determine whether to present target pedestrian in each image (such as need to carry out
Some pedestrian or some convict of trace monitoring etc.), last image processing server can be by image to be detected sequence
, image that present target pedestrian include the identification information 303 of target image 302 as target image 302, output.
The method that above-described embodiment of the application provides, by obtaining image to be detected sequence, then for mapping to be checked
As each image in sequence, which is inputted to multiple identification models of training in advance, obtain respectively with each identification
The corresponding recognition result of model, and obtained recognition result is based on, determine destination object whether is presented in the image, finally
The identification of target image is included using image in image to be detected sequence, to present destination object as target image, output
Information, determines destination object whether is presented in image so as to the corresponding recognition result of the multiple identification models of synthesis, improves
The flexibility of identification to destination object.
With further reference to Fig. 4, as the realization to method shown in above-mentioned each figure, it is used to export letter this application provides one kind
One embodiment of the device of breath, the device embodiment is corresponding with the embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 4, the device 400 for output information described in the present embodiment includes：Acquiring unit 401, configuration are used
In acquisition image to be detected sequence；Input unit 402, is configured to for each figure in above-mentioned image to be detected sequence
Picture, which is inputted to multiple identification models of training in advance, obtains recognition result corresponding with each identification model respectively,
Based on obtained recognition result, determine whether present destination object in the image；Output unit 403, being configured to will be upper
State image in image to be detected sequence, presenting above-mentioned destination object and include above-mentioned target figure as target image, output
The identification information of picture.
In some optional implementations of the present embodiment, above-mentioned multiple identification models can include human face recognition model
With at least one local identification model, wherein, above-mentioned human face recognition model can be used for the human face region to above-mentioned destination object
It is identified, each local identification model in above-mentioned at least one local identification model can be used for above-mentioned destination object
A regional area be identified.
In some optional implementations of the present embodiment, above-mentioned input unit 402 can be further configured to pair
Each image in above-mentioned image to be detected sequence, which is inputted to above-mentioned human face recognition model, obtains face knowledge
Not as a result, and the image is inputted to each local identification model, obtain corresponding with each local identification model local knowing
Other result.
In some optional implementations of the present embodiment, above-mentioned input unit 402 can be further configured to pair
Each image in above-mentioned image to be detected sequence, in response to determining that the corresponding face recognition result of the image indicates the figure
The human face region of above-mentioned destination object is not presented as in, and local recognition result corresponding with the image indicates the image institute
The quantity of the regional area of the above-mentioned destination object presented is not less than default value, determines that the image presents above-mentioned target pair
As.
In some optional implementations of the present embodiment, above-mentioned input unit 402 can be further configured to pair
Each image in above-mentioned image to be detected sequence, in response to determining that the corresponding face recognition result of the image indicates the figure
The human face region of above-mentioned destination object is presented as in, determines that the image presents above-mentioned destination object.
In some optional implementations of the present embodiment, above-mentioned input unit 402 can be further configured to pair
Each image in above-mentioned image to be detected sequence, in response to determining that the corresponding face recognition result of the image indicates the figure
The human face region of above-mentioned destination object is not presented as in, and local recognition result corresponding with the image indicates the image institute
The quantity of the regional area of the above-mentioned destination object presented is less than default value, determines that the image does not present above-mentioned target pair
As.
In some optional implementations of the present embodiment, above-mentioned at least one local identification model can include following
At least one of clothes colour recognition model, garment identification model, knapsack colour recognition model, knapsack style identification model,
Hair style identification model, cap identification model, glasses identification model, height identification model, build identification model.
The device that above-described embodiment of the application provides, image to be detected sequence is obtained by acquiring unit 401, then defeated
Enter unit 402 for each image in image to be detected sequence, which is inputted to multiple identification moulds of training in advance
Type, obtains recognition result corresponding with each identification model respectively, and is based on obtained recognition result, determine be in the image
It is no to present destination object, last output unit 403 using image in image to be detected sequence, to present destination object as
Target image, output includes the identification information of target image, true so as to the corresponding recognition result of the multiple identification models of synthesis
Determine whether present destination object in image, improve the flexibility of the identification to destination object.
Below with reference to Fig. 5, it illustrates suitable for for realizing the computer system 500 of the electronic equipment of the embodiment of the present application
Structure diagram.Electronic equipment shown in Fig. 5 is only an example, to the function of the embodiment of the present application and should not use model
Shroud carrys out any restrictions.
As shown in figure 5, computer system 500 includes central processing unit (CPU) 501, it can be read-only according to being stored in
Program in memory (ROM) 502 or be loaded into program in random access storage device (RAM) 503 from storage part 508 and
Perform various appropriate actions and processing.In RAM 503, also it is stored with system 500 and operates required various programs and data.
CPU 501, ROM 502 and RAM 503 are connected with each other by bus 504.Input/output (I/O) interface 505 is also connected to always
Line 504.
I/O interfaces 505 are connected to lower component：Importation 506 including touch-screen, touch pad etc.；Including such as liquid
The output par, c 507 of crystal display (LCD) etc. and loudspeaker etc.；Storage part 508 including hard disk etc.；And including such as
The communications portion 509 of the network interface card of LAN card, modem etc..Communications portion 509 is held via the network of such as internet
Row communication process.Driver 510 is also according to needing to be connected to I/O interfaces 505.Detachable media 511, such as semiconductor memory
Etc., it is installed on driver 510, is deposited in order to which the computer program read from it is mounted into as needed as needed
Store up part 508.
Especially, 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, it includes being carried on computer-readable medium
On computer program, the computer program include be used for execution flow chart shown in method program code.In such reality
Apply in example, which can be downloaded and installed by communications portion 509 from network, and/or from detachable media
511 are mounted.When the computer program is performed by central processing unit (CPU) 501, perform what is limited in the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer-readable recording medium either the two any combination.Computer-readable recording medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, system, device or the device of infrared ray or semiconductor, or it is any more than combination.
The more specifically example of computer-readable recording medium can include but is not limited to：Electrical connection with one or more conducting wires,
Portable computer diskette, hard disk, random access storage device (RAM), read-only storage (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer-readable recording medium can any be included or store
The tangible medium of program, the program can be commanded the either device use or in connection of execution system, device.And
In the application, computer-readable signal media can include believing in a base band or as the data that a carrier wave part is propagated
Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium beyond readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by instruction execution system, device either device use or program in connection.Included on computer-readable medium
Program code any appropriate medium can be used to transmit, include but not limited to：Wirelessly, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
Flow chart and block diagram in attached drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, the part of the module, program segment or code include one or more use
In the executable instruction of logic function as defined in realization.It should also be noted that marked at some as in the realization replaced in square frame
The function of note can also be with different from the order marked in attached drawing generation.For example, two square frames succeedingly represented are actually
It can perform substantially in parallel, they can also be performed in the opposite order sometimes, this is depending on involved function.Also to note
Meaning, the combination of each square frame and block diagram in block diagram and/or flow chart and/or the square frame in 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 application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as：A kind of processor bag
Include acquiring unit, input unit and output unit.Wherein, the title of these units is not formed to the unit under certain conditions
The restriction of itself, for example, acquiring unit is also described as " unit for obtaining image to be detected sequence ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in device described in above-described embodiment；Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine computer-readable recording medium carries one or more program, when said one or multiple programs are performed by the device so that should
Device：Obtain image to be detected sequence；For each image in image to be detected sequence, which is inputted to advance
Trained multiple identification models, obtain recognition result corresponding with each identification model respectively, based on obtained recognition result,
Determine whether present destination object in the image；By image in image to be detected sequence, to present the destination object
As target image, output includes the identification information of the target image.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from foregoing invention design, carried out by above-mentioned technical characteristic or its equivalent feature
The other technical solutions for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical solution that the technical characteristic of energy is replaced mutually and formed.
Claims (16)
1. a kind of method for output information, including：
Obtain image to be detected sequence；
For each image in image to be detected sequence, which is inputted to multiple identification moulds of training in advance
Type, obtains recognition result corresponding with each identification model respectively, based on obtained recognition result, determine in the image whether
Present destination object；
Institute is included using image in image to be detected sequence, presenting the destination object as target image, output
State the identification information of target image.
2. the method according to claim 1 for output information, wherein, the multiple identification model includes recognition of face
Model and at least one local identification model, the human face recognition model are used to know the human face region of the destination object
Not, each local identification model at least one local identification model is used for a part to the destination object
Region is identified.
3. the method according to claim 2 for output information, wherein, it is described in image to be detected sequence
Each image, by the image input in advance training multiple identification models, obtain corresponding with each identification model respectively
Recognition result, including：
For each image in image to be detected sequence, which is inputted to the human face recognition model, is obtained
Face recognition result, and the image is inputted to each local identification model, obtain corresponding with each local identification model
Local recognition result.
4. the method according to claim 3 for output information, wherein, it is described to be based on obtained recognition result, really
Destination object whether is presented in the fixed image, including：
For each image in image to be detected sequence, in response to determining that the corresponding face recognition result of the image refers to
Show the human face region for not presenting the destination object in the image, and local recognition result instruction corresponding with the image should
The quantity of the regional area for the destination object that image is presented is not less than default value, determines that the image presents the mesh
Mark object.
5. the method according to claim 3 for output information, wherein, it is described to be based on obtained recognition result, really
Destination object whether is presented in the fixed image, including：
For each image in image to be detected sequence, in response to determining that the corresponding face recognition result of the image refers to
Show the human face region that the destination object is presented in the image, determine that the image presents the destination object.
6. the method according to claim 3 for output information, wherein, it is described to be based on obtained recognition result, really
Destination object whether is presented in the fixed image, including：
For each image in image to be detected sequence, in response to determining that the corresponding face recognition result of the image refers to
Show the human face region for not presenting the destination object in the image, and local recognition result instruction corresponding with the image should
The quantity of the regional area for the destination object that image is presented is less than default value, determines that the image does not present the mesh
Mark object.
7. the method for output information according to one of claim 2-6, wherein, at least one local identification mould
Type includes at least one of following：Clothes colour recognition model, garment identification model, knapsack colour recognition model, knapsack money
Formula identification model, hair style identification model, cap identification model, glasses identification model, height identification model, build identification model.
8. a kind of device for output information, including：
Acquiring unit, is configured to obtain image to be detected sequence；
Input unit, is configured to, for each image in image to be detected sequence, which be inputted to advance
Trained multiple identification models, obtain recognition result corresponding with each identification model respectively, based on obtained recognition result,
Determine whether present destination object in the image；
Output unit, is configured to using image in image to be detected sequence, presenting the destination object as mesh
Logo image, output include the identification information of the target image.
9. the device according to claim 8 for output information, wherein, the multiple identification model includes recognition of face
Model and at least one local identification model, the human face recognition model are used to know the human face region of the destination object
Not, each local identification model at least one local identification model is used for a part to the destination object
Region is identified.
10. the device according to claim 9 for output information, wherein, the input unit is further configured to：
For each image in image to be detected sequence, which is inputted to the human face recognition model, is obtained
Face recognition result, and the image is inputted to each local identification model, obtain corresponding with each local identification model
Local recognition result.
11. the device according to claim 10 for output information, wherein, the input unit further configures use
In：
For each image in image to be detected sequence, in response to determining that the corresponding face recognition result of the image refers to
Show the human face region for not presenting the destination object in the image, and local recognition result instruction corresponding with the image should
The quantity of the regional area for the destination object that image is presented is not less than default value, determines that the image presents the mesh
Mark object.
12. the device according to claim 10 for output information, wherein, the input unit further configures use
In：
For each image in image to be detected sequence, in response to determining that the corresponding face recognition result of the image refers to
Show the human face region that the destination object is presented in the image, determine that the image presents the destination object.
13. the device according to claim 10 for output information, wherein, the input unit further configures use
In：
For each image in image to be detected sequence, in response to determining that the corresponding face recognition result of the image refers to
Show the human face region for not presenting the destination object in the image, and local recognition result instruction corresponding with the image should
The quantity of the regional area for the destination object that image is presented is less than default value, determines that the image does not present the mesh
Mark object.
14. the device for output information according to one of claim 9-13, wherein, at least one local identification
Model includes at least one of following：Clothes colour recognition model, garment identification model, knapsack colour recognition model, knapsack
Style identification model, hair style identification model, cap identification model, glasses identification model, height identification model, build identification mould
Type.
15. a kind of electronic equipment, including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are performed 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 recording medium, is stored thereon with computer program, wherein, when which is executed by processor
Realize the method as described in any in claim 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711455262.7A CN108038473B (en) | 2017-12-28 | 2017-12-28 | Method and apparatus for outputting information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711455262.7A CN108038473B (en) | 2017-12-28 | 2017-12-28 | Method and apparatus for outputting information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108038473A true CN108038473A (en) | 2018-05-15 |
| CN108038473B CN108038473B (en) | 2021-04-23 |
Family
ID=62098093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711455262.7A Active CN108038473B (en) | 2017-12-28 | 2017-12-28 | Method and apparatus for outputting information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108038473B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084306A (en) * | 2019-04-30 | 2019-08-02 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating dynamic image |
| CN111783515A (en) * | 2020-03-18 | 2020-10-16 | 北京沃东天骏信息技术有限公司 | Behavior action recognition method and device |
| CN113067966A (en) * | 2021-02-03 | 2021-07-02 | 深兰科技（上海）有限公司 | Target image acquisition equipment and method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6674877B1 (en) * | 2000-02-03 | 2004-01-06 | Microsoft Corporation | System and method for visually tracking occluded objects in real time |
| CN1916931A (en) * | 2005-08-19 | 2007-02-21 | 上海正电科技发展有限公司 | Method of searching specific characteristic portrait in video from monitored street |
| CN102665054A (en) * | 2012-05-10 | 2012-09-12 | 江苏友上科技实业有限公司 | Network video recorder system for fast face retrieval |
| CN104794458A (en) * | 2015-05-07 | 2015-07-22 | 北京丰华联合科技有限公司 | Fuzzy video person identifying method |
| CN105893510A (en) * | 2016-03-30 | 2016-08-24 | 北京格灵深瞳信息技术有限公司 | Video structurization system and target search method thereof |
| CN106127173A (en) * | 2016-06-30 | 2016-11-16 | 北京小白世纪网络科技有限公司 | A kind of human body attribute recognition approach based on degree of depth study |
| CN106650577A (en) * | 2016-09-22 | 2017-05-10 | 江苏理工学院 | Fast retrieval method and fast retrieval system for target person in monitoring video data file |
| CN106874884A (en) * | 2017-03-03 | 2017-06-20 | 中国民航大学 | Human body recognition methods again based on position segmentation |
| CN107341445A (en) * | 2017-06-07 | 2017-11-10 | 武汉大千信息技术有限公司 | The panorama of pedestrian target describes method and system under monitoring scene |
-
2017
- 2017-12-28 CN CN201711455262.7A patent/CN108038473B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6674877B1 (en) * | 2000-02-03 | 2004-01-06 | Microsoft Corporation | System and method for visually tracking occluded objects in real time |
| CN1916931A (en) * | 2005-08-19 | 2007-02-21 | 上海正电科技发展有限公司 | Method of searching specific characteristic portrait in video from monitored street |
| CN102665054A (en) * | 2012-05-10 | 2012-09-12 | 江苏友上科技实业有限公司 | Network video recorder system for fast face retrieval |
| CN104794458A (en) * | 2015-05-07 | 2015-07-22 | 北京丰华联合科技有限公司 | Fuzzy video person identifying method |
| CN105893510A (en) * | 2016-03-30 | 2016-08-24 | 北京格灵深瞳信息技术有限公司 | Video structurization system and target search method thereof |
| CN106127173A (en) * | 2016-06-30 | 2016-11-16 | 北京小白世纪网络科技有限公司 | A kind of human body attribute recognition approach based on degree of depth study |
| CN106650577A (en) * | 2016-09-22 | 2017-05-10 | 江苏理工学院 | Fast retrieval method and fast retrieval system for target person in monitoring video data file |
| CN106874884A (en) * | 2017-03-03 | 2017-06-20 | 中国民航大学 | Human body recognition methods again based on position segmentation |
| CN107341445A (en) * | 2017-06-07 | 2017-11-10 | 武汉大千信息技术有限公司 | The panorama of pedestrian target describes method and system under monitoring scene |
Non-Patent Citations (2)
| Title |
|---|
| 孙伟: "《基于人体外貌特征的自适应检测与跟踪算法的研究与实现》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李邵梅 等；: "《基于局部深度匹配的行人再识别》", 《计算机应用研究》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084306A (en) * | 2019-04-30 | 2019-08-02 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating dynamic image |
| CN110084306B (en) * | 2019-04-30 | 2022-03-29 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating dynamic image |
| CN111783515A (en) * | 2020-03-18 | 2020-10-16 | 北京沃东天骏信息技术有限公司 | Behavior action recognition method and device |
| CN113067966A (en) * | 2021-02-03 | 2021-07-02 | 深兰科技（上海）有限公司 | Target image acquisition equipment and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108038473B (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214343A (en) | Method and apparatus for generating face critical point detection model | |
| CN108154196B (en) | Method and apparatus for exporting image | |
| CN107644209A (en) | Method for detecting human face and device | |
| CN108010008B (en) | Target tracking method and device and electronic equipment | |
| CN107909065A (en) | The method and device blocked for detecting face | |
| CN108256479A (en) | Face tracking method and device | |
| CN108133201B (en) | Face character recognition methods and device | |
| CN108985259A (en) | Human motion recognition method and device | |
| CN108446387A (en) | Method and apparatus for updating face registration library | |
| CN108416324A (en) | Method and apparatus for detecting live body | |
| CN109308490A (en) | Method and apparatus for generating information | |
| CN108038880A (en) | Method and apparatus for handling image | |
| CN110110811A (en) | Method and apparatus for training pattern, the method and apparatus for predictive information | |
| CN107622240A (en) | Method for detecting human face and device | |
| CN108171204B (en) | Detection method and device | |
| CN108229376A (en) | For detecting the method and device of blink | |
| CN109376267A (en) | Method and apparatus for generating model | |
| CN109165573A (en) | Method and apparatus for extracting video feature vector | |
| CN109447156A (en) | Method and apparatus for generating model | |
| CN109145828A (en) | Method and apparatus for generating video classification detection model | |
| CN108197618A (en) | For generating the method and apparatus of Face datection model | |
| CN108133197A (en) | For generating the method and apparatus of information | |
| CN108510454A (en) | Method and apparatus for generating depth image | |
| CN109447246A (en) | Method and apparatus for generating model | |
| CN108038473A (en) | Method and apparatus for output information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |