CN107862259A - Human image collecting method and device, terminal installation and computer-readable recording medium - Google Patents
Human image collecting method and device, terminal installation and computer-readable recording medium Download PDFInfo
- Publication number
- CN107862259A CN107862259A CN201711003051.XA CN201711003051A CN107862259A CN 107862259 A CN107862259 A CN 107862259A CN 201711003051 A CN201711003051 A CN 201711003051A CN 107862259 A CN107862259 A CN 107862259A
- Authority
- CN
- China
- Prior art keywords
- cameras
- portrait
- image
- roi
- depth 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
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
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present invention provides a kind of human image collecting method, applied to terminal, gathers the image for including different characteristic information respectively using a variety of cameras of the terminal.The image zooming-out character contour collected using the RGB cameras and the IR cameras, the image collected using the TOF cameras obtain depth information；According to the character contour and the depth information comprehensive analysis, the portrait gathered.The embodiment of the present invention also provides a kind of portrait collecting apparatus, terminal installation and computer-readable recording medium.Human image collecting precision can be improved using the embodiment of the present invention, more accurately removes image background.
Description
Technical field
The present invention relates to field of terminal technology, more particularly to a kind of human image collecting method and device, terminal installation and calculating
Machine readable storage medium storing program for executing.
Background technology
This part is it is intended that the embodiment for the embodiment of the present invention stated in claims and embodiment carries
For background or context.Description herein recognizes it is prior art not because not being included in this part.
It is not high personage's edge definition to be present in the existing character contour extractive technique in natural background, and algorithm is complicated, computing
Measure huge, edge shake, pair with figure picture with color background identification it is wrong the problems such as, cause universal theory technology to be unable to reach business
With level, real experiences are ineffective, and this technology gathers the image for including different characteristic information, root respectively using a variety of cameras
Comprehensive analysis is carried out according to character contour and the depth information collected, so as to the portrait gathered, can be had using this technology
The solution of effect improves foregoing problems.
The content of the invention
In consideration of it, a kind of human image collecting method provided by the invention, portrait collecting apparatus, terminal installation and computer-readable
Storage medium, it is possible to increase human image collecting precision, more accurately remove image background, and application is more flexible.
On the one hand the embodiment of the present invention provides a kind of human image collecting method, applied to terminal, methods described includes following step
Suddenly：
Being gathered respectively using a variety of cameras of the terminal includes the image of different characteristic information；A variety of cameras
Including：RGB cameras, IR cameras and TOF cameras；
The image zooming-out character contour collected using the RGB cameras and the IR cameras；And obtain the TOF
The depth information for the image that camera collects；
Each figure collected according to the character contour and the depth information to a variety of cameras carries out total score
Analysis is handled, the portrait gathered.
Further, it is described to obtain the TOF cameras in above-mentioned human image collecting method provided in an embodiment of the present invention
The depth information of the image collected includes：
Obtain the depth information in the first ROI and scene for the image that the TOF cameras collect；
The image zooming-out character contour collected using the IR cameras is included：
The image collected using the IR cameras obtains the 2nd ROI and portrait position's information.
Further, it is described according to the character contour in above-mentioned human image collecting method provided in an embodiment of the present invention
And each figure that the depth information collects to a variety of cameras carries out comprehensive analysis processing, the portrait bag gathered
Include：
Portrait ROI is obtained according to the first ROI and the 2nd ROI；
According to the portrait depth information of portrait described in the depth information and portrait position's acquisition of information；
The portrait is handled using the portrait ROI and the portrait depth information, obtains the people of the collection
Picture.
Further, in above-mentioned human image collecting method provided in an embodiment of the present invention, according to the first ROI with it is described
2nd ROI, which obtains portrait ROI, to be included：
Confirm the first ROI and the 2nd ROI overlapping region；
The portrait ROI is confirmed as into the overlapping region.
Further, in above-mentioned human image collecting method provided in an embodiment of the present invention, what the IR cameras collected
The image that image obtains using background infrared illumination source, the light source of the background infrared illumination are invisible using 850nm
Light.
Further, in above-mentioned human image collecting method provided in an embodiment of the present invention, according to the depth information and institute
Stating the portrait depth of portrait described in portrait position's acquisition of information includes：
According to the depth information in the scene and portrait position's information, the depth information of portrait position is judged；
Background in scene and the object in front of the human body being taken are excluded by the depth information of the portrait position.
Further, in above-mentioned human image collecting method provided in an embodiment of the present invention, methods described also includes：Described
In portrait ROI portrait is obtained using RGB portraits detection algorithm.
On the other hand the embodiment of the present invention also provides a kind of portrait collecting apparatus, applied to terminal, the human image collecting dress
Put including：
Acquisition module, the image of different characteristic information is included for being gathered respectively using a variety of cameras of the terminal；
A variety of cameras include：RGB cameras, IR cameras and TOF cameras；
Extraction module, for the image zooming-out character contour collected using the RGB cameras and the IR cameras；
Acquisition module, the depth information of the image collected for obtaining the TOF cameras；
Processing module, it is each for being collected according to the character contour and the depth information to a variety of cameras
Image carries out comprehensive analysis processing, the portrait gathered.
Another further aspect of the embodiment of the present invention also provides a kind of terminal installation, and the terminal installation includes memory and processing
Device, the memory are used to store at least one instruction, and the processor is used to perform the computer program stored in memory
The step in human image collecting method described in the above-mentioned any one of Shi Shixian.
The another aspect of the embodiment of the present invention also provides a kind of computer-readable recording medium, the computer-readable storage medium
Matter is stored with least one instruction, and at least one instruction realizes described human image collecting method, institute when being executed by processor
Stating human image collecting method includes the step in the human image collecting method described in above-mentioned any one.
Human image collecting method and device, terminal installation and computer-readable recording medium provided in an embodiment of the present invention, profit
Being gathered respectively with a variety of cameras of the terminal includes the image of different characteristic information.Utilize RGB cameras and described
The image zooming-out character contour that IR cameras collect, the image collected using the TOF cameras obtain depth information；Root
According to the character contour and the depth information comprehensive analysis, the portrait gathered.It can be improved using the embodiment of the present invention
Human image collecting precision, more accurately remove image background.
Further, human image collecting method and device provided in an embodiment of the present invention, terminal installation and computer-readable deposit
Storage media, the image that the image that the IR cameras collect obtains using background infrared illumination source, the background are red
The light source of outer illumination uses 850nm black lights.The background infrared illumination, camera is directly entered using infrared light, with quilt
There is great luminance difference in the region that human body blocks no infrared direct projection, it is thus possible to which more accurately analysis, which identifies, belongs to human body
Part, interference is reduced, improve precision.
Brief description of the drawings
Fig. 1 is the flow chart of the human image collecting method of first embodiment of the invention.
Fig. 2 is the flow chart of the human image collecting method of first embodiment of the invention.
Fig. 3 is the structural representation of the terminal of an embodiment of the present invention.
Fig. 4 is the exemplary functional block diagram of the terminal shown in Fig. 3.
Main element symbol description
| Terminal | 1 |
| Storage device | 10 |
| Display screen | 20 |
| Processor | 30 |
| Acquisition module | 11 |
| Extraction module | 12 |
| Acquisition module | 13 |
| Processing module | 14 |
Embodiment
In order to be more clearly understood that the above-mentioned purpose of the embodiment of the present invention, feature and advantage, below in conjunction with the accompanying drawings and
The present invention will be described in detail for embodiment.It should be noted that in the case where not conflicting, the embodiment party of the application
Feature in formula can be mutually combined.
Many details are elaborated in the following description in order to fully understand the embodiment of the present invention, described reality
The mode of applying is a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, ability
The every other embodiment that domain those of ordinary skill is obtained under the premise of creative work is not made, belongs to the present invention
The scope of embodiment protection.
Unless otherwise defined, technology of all of technologies and scientific terms used here by the article with belonging to the embodiment of the present invention
The implication that the technical staff in field is generally understood that is identical.Term used in the description of the invention herein is intended merely to
The purpose of specific embodiment is described, it is not intended that in the limitation embodiment of the present invention.
Fig. 1 is the flow chart of the human image collecting method of first embodiment of the invention.The human image collecting method is applied to
Terminal, the terminal can be the smart machines such as smart mobile phone, notebook computer, desk-top/tablet personal computer, intelligent watch.
As shown in figure 1, the human image collecting method comprises the following steps：
101：Being gathered respectively using a variety of cameras of the terminal includes the image of different characteristic information；It is described a variety of to take the photograph
As head includes：RGB cameras, IR cameras and TOF cameras.
In present embodiment, the TOF camera collection images obtain the depth information in the first ROI and scene, described
IR camera collection images obtain the 2nd ROI and portrait position's information, and the image that the IR cameras collect is using the back of the body
The image that scape infrared illumination source obtains, the light source of the background infrared illumination use 850nm black lights.The light source is located at
Human body rear, uniformly dispersing irradiate to human body direction, and the IR cameras gather the dash area in camera lens in front of human body,
Therefrom identify the part for belonging to human body.Infrared light is directly entered in camera, the area with being blocked no infrared direct projection by human body
There is great luminance difference in domain, can accurately analyze and identify the part for belonging to human body.
102：The image zooming-out character contour collected using the RGB cameras and the IR cameras；And obtain institute
State the depth information for the image that TOF cameras collect.
In present embodiment, portrait ROI is obtained according to the first ROI and the 2nd ROI, the first ROI and described the
Confirm as the portrait ROI in two ROI overlapping region.According to people described in the depth information and portrait position's acquisition of information
Portrait position's depth information of picture, the portrait is handled using the portrait ROI and the portrait depth information, obtained
The portrait of the collection.
103：Each figure collected according to the character contour and the depth information to a variety of cameras carries out comprehensive
Close analyzing and processing, the portrait gathered.
In present embodiment, according to the depth information in the scene and portrait position's information, people's image position is judged
The depth information put, the background in scene and the thing in front of the human body being taken are excluded by the depth information of the portrait position
Body.The portrait is handled according to the portrait ROI and the portrait depth information, obtains the portrait of the collection.
In the portrait of the collection portrait is obtained using RGB portraits detection algorithm.
The human image collecting method that present embodiment provides, is gathered including difference respectively using a variety of cameras of the terminal
The image of characteristic information；A variety of cameras include：RGB cameras, IR cameras and TOF cameras；Taken the photograph using the RGB
The image zooming-out character contour collected as head and the IR cameras；And obtain the image that the TOF cameras collect
Depth information；Each figure collected according to the character contour and the depth information to a variety of cameras carries out total score
Analysis is handled, the portrait gathered.It thus can more accurately analyze and identify the part for belonging to human body, reduce interference, improve
Precision, more bases for estimation are provided for identification collection figure information, so as to improve Identification of Images precision.
Fig. 2 is the flow chart of the human image collecting method of second embodiment of the invention.Described second embodiment and the
The main distinction of one embodiment is, is the embodiment that step more refines in second embodiment.It should be noted that
In the range of the spirit or essential attributes of the embodiment of the present invention, each concrete scheme suitable for first embodiment can also phase
Answer suitable for second embodiment, for the sake of saving space and avoiding repetition, just repeat no more herein.
As shown in Fig. 2 the human image collecting method comprises the following steps：
201：Being gathered respectively using a variety of cameras of the terminal includes the image of different characteristic information；It is described a variety of to take the photograph
As head includes：RGB cameras, IR cameras and TOF cameras.
202：The image zooming-out character contour collected using the RGB cameras and the IR cameras；And obtain institute
State the depth information for the image that TOF cameras collect.
203：Obtain the depth information in the first ROI and scene for the image that the TOF cameras collect；Using described
The image that IR cameras collect obtains the 2nd ROI and portrait position's information.
204：Confirm the first ROI and the 2nd ROI overlapping region, the overlapping region is portrait ROI；According to
Portrait position's depth information of portrait described in the depth information and portrait position's acquisition of information.
205：Each figure collected according to the character contour and the depth information to a variety of cameras carries out comprehensive
Close analyzing and processing, the portrait gathered.
The human image collecting method that present embodiment provides, in addition to the technique effect with first embodiment, refine the
The step of in one embodiment between 102 and 103.Gathered using a variety of cameras of the terminal and believed including different characteristic respectively
The image of breath；A variety of cameras include：RGB cameras, IR cameras and TOF cameras；Using the RGB cameras and
The image zooming-out character contour that the IR cameras collect；And obtain the depth letter for the image that the TOF cameras collect
Breath；Obtain the depth information in the first ROI and scene for the image that the TOF cameras collect；Utilize the IR cameras
The image collected obtains the 2nd ROI and portrait position's information；Confirm the first ROI and the 2nd ROI overlapping region,
The overlapping region is portrait ROI；According to people's image position of portrait described in the depth information and portrait position's acquisition of information
Put depth information；Integrated according to each figure that the character contour and the depth information collect to a variety of cameras
Analyzing and processing, the portrait gathered.The depth information of the portrait position can exclude the background in scene and be taken
Object in front of human body.More bases for estimation are provided for identification collection figure information, so as to improve Identification of Images precision.
Above is the detailed description that the method provided the embodiment of the present invention is carried out.According to different demands, shown stream
The execution sequence of square can change in journey figure, and some squares can omit.The terminal provided below the embodiment of the present invention
It is described.
The embodiment of the present invention also provides a kind of computer equipment, including memory, processor and storage are on a memory simultaneously
The computer program that can be run on a processor, institute in any of the above-described embodiment is realized during the computing device described program
The step of human image collecting method stated.
Fig. 3 is in an embodiment of the present invention, there is provided terminal/computer equipment using the respective embodiments described above
Structural representation.As shown in figure 3, terminal 1 includes storage device 10.Described terminal 1 can be mobile phone, tablet personal computer, individual
Digital assistants etc. have the terminal of human image collecting function.Described terminal 1 can utilize a variety of cameras of the terminal to distinguish
Collection includes the image of different characteristic information；A variety of cameras include：RGB cameras, IR cameras and TOF cameras；
The image zooming-out character contour collected using the RGB cameras and the IR cameras；And obtain the TOF cameras and adopt
The depth information of the image collected；A variety of cameras are collected according to the character contour and the depth information each
Figure carries out comprehensive analysis processing, the portrait gathered.It thus can more accurately analyze and identify the part for belonging to human body, subtract
Few interference, improves precision, more bases for estimation is provided for identification collection figure information, so as to improve Identification of Images precision.
The terminal 1 can also utilize a variety of cameras of the terminal to gather the figure for including different characteristic information respectively
Picture；A variety of cameras include：RGB cameras, IR cameras and TOF cameras；Utilize the RGB cameras and the IR
The image zooming-out character contour that camera collects；And obtain the depth information for the image that the TOF cameras collect；Obtain
Depth information in the first ROI and scene of the image that the TOF cameras collect；Collected using the IR cameras
Image obtains the 2nd ROI and portrait position's information；Confirm the first ROI and the 2nd ROI overlapping region, the coincidence
Region is portrait ROI；Believed according to portrait position's depth of portrait described in the depth information and portrait position's acquisition of information
Breath；Each figure collected according to the character contour and the depth information to a variety of cameras is carried out at comprehensive analysis
Reason, the portrait gathered.Before the depth information of the portrait position can exclude the background in scene and the human body being taken
The object of side.More bases for estimation are provided for identification collection figure information, so as to improve Identification of Images precision.
In present embodiment, terminal 1 is a mobile phone.Terminal 1 can also include display screen 20 and processor 30.Storage device
10th, display screen 20 can electrically connect with processor 30 respectively.
Described storage device 10 can be different type storage device, for storing Various types of data.For example, it may be eventually
Memory, the internal memory at end 1, can also be the storage card that can be external in the terminal 1, such as flash memory, SM cards (Smart Media
Card, smart media card), SD card (Secure Digital Card, safe digital card) etc..In addition, memory can include height
Fast random access memory, nonvolatile memory, such as hard disk, internal memory, plug-in type hard disk, intelligent memory card can also be included
(Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card), at least
One disk memory, flush memory device or other volatile solid-state parts.Storage device 10 is used to store all kinds of numbers
According to for example, the types of applications program (Applications) installed in the terminal 1, setting using above-mentioned human image collecting method
The information such as the data put, obtained.
Display screen 20 is installed on terminal 1, for display information.
Processor 30 is used for all kinds of softwares for performing installation in the human image collecting method and the terminal 1, such as grasps
Make system and human image collecting software etc..Processor 30 including but not limited to processor (Central Processing Unit,
CPU), micro-control unit (Micro Controller Unit, MCU) etc. is used for interpretive machine instruction and handles computer
The device of data in software.
Described terminal 1 can include one or more modules, and one or more of modules are stored in terminal 1
In storage device 10 and it is configured to be performed by one or more processors (present embodiment is a processor 30), to complete
The embodiment of the present invention.For example, as shown in fig.4, the terminal 1 can include acquisition module 11, extraction module 12, acquisition module
13rd, processing module 14.Module alleged by the embodiment of the present invention can complete the program segment of a specific function, be more suitable for than program
In the implementation procedure of description software within a processor.
It is understood that each embodiment in corresponding above-mentioned human image collecting method, terminal 1 can include institute in Fig. 4
Part or all in each functional module shown, the function of each module will introduced in detail below.More than it should be noted that
In each embodiment of human image collecting method identical noun related terms and its it is specific illustrate be readily applicable to
Under to the function introduction of each module.For the sake of saving space and avoiding repetition, just repeat no more herein.
Acquisition module 11 is used to gather the image for including different characteristic information respectively using a variety of cameras of the terminal；
A variety of cameras include：RGB cameras, IR cameras and TOF cameras.
The image zooming-out personage that extraction module 12 is used to collect using the RGB cameras and the IR cameras takes turns
It is wide.
Acquisition module 13 is used for the depth information for obtaining the image that the TOF cameras collect.
Processing module 14 is used for a variety of cameras are collected according to the character contour and the depth information
Each image carries out comprehensive analysis processing, the portrait gathered.
The embodiment of the present invention also provides a kind of computer-readable recording medium, is stored thereon with computer program, the meter
Calculation machine program realizes the step of human image collecting method in any of the above-described embodiment when being executed by processor.
If the integrated module/unit of the portrait collecting apparatus/terminal/computer equipment is with the shape of SFU software functional unit
Formula is realized and is used as independent production marketing or in use, can be stored in a computer read/write memory medium.It is based on
Such understanding, the present invention realize all or part of flow in above-mentioned embodiment method, can also pass through computer program
To instruct the hardware of correlation to complete, described computer program can be stored in a computer-readable recording medium, the calculating
Machine program when being executed by processor, can be achieved above-mentioned each embodiment of the method the step of.Wherein, the computer program includes
Computer program code, the computer program code can be source code form, object identification code form, executable file or certain
A little intermediate forms etc..The computer-readable recording medium can include：Any of the computer program code can be carried
Entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disc, CD, computer storage, read-only storage (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and
Software distribution medium etc..
Alleged processor can be CPU (Central Processing Unit, CPU), can also be it
His general processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other PLDs, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng the processor is the control centre of the portrait collecting apparatus/terminal, utilizes various interfaces and the whole portrait of connection
The various pieces of harvester/terminal.
The memory is used to store the computer program and/or module, and the processor is deposited by running or performing
Computer program and/or module in the memory are stored up, and calls the data being stored in memory, realizes the people
As the various functions of harvester/terminal.The memory can mainly include storing program area and storage data field, wherein, deposit
Storing up program area can storage program area, application program (such as sound-playing function, image player work(needed at least one function
Can etc.) etc.；Storage data field can store uses created data (such as voice data, phone directory etc.) etc. according to mobile phone.
In addition, memory can include high-speed random access memory, nonvolatile memory can also be included, for example, hard disk, internal memory,
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, dodge
Deposit card (Flash Card), at least one disk memory, flush memory device or other volatile solid-state parts.
It is obvious to a person skilled in the art that the embodiment of the present invention is not limited to the details of above-mentioned one exemplary embodiment,
And in the case of the spirit or essential attributes without departing substantially from the embodiment of the present invention, this hair can be realized in other specific forms
Bright embodiment.Therefore, no matter from the point of view of which point, embodiment all should be regarded as exemplary, and is nonrestrictive, sheet
The scope of inventive embodiments is limited by appended claims rather than described above, it is intended that will fall being equal in claim
All changes in the implication and scope of important document are included in the embodiment of the present invention.Should not be by any accompanying drawing mark in claim
Note is considered as the involved claim of limitation.Furthermore, it is to be understood that the word of " comprising " one is not excluded for other units or step, odd number is not excluded for
Plural number.
Embodiment of above is only unrestricted to illustrate the technical scheme of the embodiment of the present invention, although with reference to more than preferably
The embodiment of the present invention is described in detail embodiment, it will be understood by those within the art that, can be to this hair
The technical scheme of bright embodiment is modified or equivalent substitution should not all depart from the embodiment of the present invention technical scheme spirit.
Claims (10)
- A kind of 1. human image collecting method, applied to terminal, it is characterised in that the described method comprises the following steps：Being gathered respectively using a variety of cameras of the terminal includes the image of different characteristic information；A variety of camera bags Include：RGB cameras, IR cameras and TOF cameras；The image zooming-out character contour collected using the RGB cameras and the IR cameras；And obtain the TOF shootings The depth information for the image that head collects；Each figure collected according to the character contour and the depth information to a variety of cameras is carried out at comprehensive analysis Reason, the portrait gathered.
- 2. human image collecting method according to claim 1, it is characterised in that the acquisition TOF cameras collect The depth information of image include：Obtain the depth information in the first ROI and scene for the image that the TOF cameras collect；The image zooming-out character contour collected using the IR cameras is included：The image collected using the IR cameras obtains the 2nd ROI and portrait position's information.
- 3. human image collecting method according to claim 2, it is characterised in that described according to the character contour and the depth Each figure that degree information collects to a variety of cameras carries out comprehensive analysis processing, and the portrait gathered includes：Portrait ROI is obtained according to the first ROI and the 2nd ROI；According to the portrait depth information of portrait described in the depth information and portrait position's acquisition of information；The portrait is handled using the portrait ROI and the portrait depth information, obtains the portrait of the collection.
- 4. human image collecting method according to claim 3, it is characterised in that obtained according to the first ROI and the 2nd ROI Include to portrait ROI：Confirm the first ROI and the 2nd ROI overlapping region；The portrait ROI is confirmed as into the overlapping region.
- 5. human image collecting method according to claim 2, it is characterised in that the image that the IR cameras collect includes profit The image obtained with background infrared illumination source, the light source of the background infrared illumination use 850nm black lights.
- 6. according to the human image collecting method of claim 3 or 4, it is characterised in that according to the depth information and the portrait The portrait depth that positional information obtains the portrait includes：According to the depth information in the scene and portrait position's information, the depth information of portrait position is judged；Background in scene and the object in front of the human body being taken are excluded by the depth information of the portrait position.
- 7. human image collecting method according to claim 6, it is characterised in that methods described also includes：In the portrait ROI Portrait is obtained using RGB portraits detection algorithm.
- 8. a kind of portrait collecting apparatus, applied to terminal, it is characterised in that described device includes：Acquisition module：Include the image of different characteristic information for being gathered respectively using a variety of cameras of the terminal；It is described A variety of cameras include：RGB cameras, IR cameras and TOF cameras；Extraction module, for the image zooming-out character contour collected using the RGB cameras and the IR cameras；Acquisition module, the depth information of the image collected for obtaining the TOF cameras；Processing module, for each image collected according to the character contour and the depth information to a variety of cameras Carry out comprehensive analysis processing, the portrait gathered.
- 9. a kind of terminal installation, it is characterised in that the terminal installation includes memory and processor, and the memory is used to deposit At least one instruction is stored up, the processor is used to perform at least one instruction to realize claim 1-7 any one institute Step in the human image collecting method stated.
- 10. a kind of computer-readable recording medium, is stored thereon with computer instruction, it is characterised in that：The computer instruction The step of human image collecting method as described in any one in claim 1-7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711003051.XA CN107862259A (en) | 2017-10-24 | 2017-10-24 | Human image collecting method and device, terminal installation and computer-readable recording medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711003051.XA CN107862259A (en) | 2017-10-24 | 2017-10-24 | Human image collecting method and device, terminal installation and computer-readable recording medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107862259A true CN107862259A (en) | 2018-03-30 |
Family
ID=61697272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711003051.XA Pending CN107862259A (en) | 2017-10-24 | 2017-10-24 | Human image collecting method and device, terminal installation and computer-readable recording medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107862259A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108564613A (en) * | 2018-04-12 | 2018-09-21 | 维沃移动通信有限公司 | A kind of depth data acquisition methods and mobile terminal |
| WO2019233106A1 (en) * | 2018-06-06 | 2019-12-12 | Oppo广东移动通信有限公司 | Image acquisition method and device, image capture device, computer apparatus, and readable storage medium |
| CN112532854A (en) * | 2019-09-17 | 2021-03-19 | 华为技术有限公司 | Image processing method and electronic equipment |
| US11205071B2 (en) | 2018-07-16 | 2021-12-21 | Advanced New Technologies Co., Ltd. | Image acquisition method, apparatus, system, and electronic device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106210568A (en) * | 2016-07-15 | 2016-12-07 | 深圳奥比中光科技有限公司 | Image processing method and device |
| CN107277481A (en) * | 2017-07-14 | 2017-10-20 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
-
2017
- 2017-10-24 CN CN201711003051.XA patent/CN107862259A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106210568A (en) * | 2016-07-15 | 2016-12-07 | 深圳奥比中光科技有限公司 | Image processing method and device |
| CN107277481A (en) * | 2017-07-14 | 2017-10-20 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108564613A (en) * | 2018-04-12 | 2018-09-21 | 维沃移动通信有限公司 | A kind of depth data acquisition methods and mobile terminal |
| WO2019233106A1 (en) * | 2018-06-06 | 2019-12-12 | Oppo广东移动通信有限公司 | Image acquisition method and device, image capture device, computer apparatus, and readable storage medium |
| US11205071B2 (en) | 2018-07-16 | 2021-12-21 | Advanced New Technologies Co., Ltd. | Image acquisition method, apparatus, system, and electronic device |
| US11244158B2 (en) | 2018-07-16 | 2022-02-08 | Advanced New Technologies Co., Ltd. | Image acquisition method, apparatus, system, and electronic device |
| CN112532854A (en) * | 2019-09-17 | 2021-03-19 | 华为技术有限公司 | Image processing method and electronic equipment |
| CN112532854B (en) * | 2019-09-17 | 2022-05-31 | 华为技术有限公司 | Image processing method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359538B (en) | Training method of convolutional neural network, gesture recognition method, device and equipment | |
| EP3916627A1 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| CN107862259A (en) | Human image collecting method and device, terminal installation and computer-readable recording medium | |
| CN108765278A (en) | A kind of image processing method, mobile terminal and computer readable storage medium | |
| US20200410723A1 (en) | Image Synthesis Method And Apparatus | |
| CN103679147A (en) | Method and device for identifying model of mobile phone | |
| CN107871125A (en) | Architecture against regulations recognition methods, device and electronic equipment | |
| CN111310705A (en) | Image recognition method and device, computer equipment and storage medium | |
| US10650234B2 (en) | Eyeball movement capturing method and device, and storage medium | |
| CN107844742B (en) | Facial image glasses minimizing technology, device and storage medium | |
| EP4033458A2 (en) | Method and apparatus of face anti-spoofing, device, storage medium, and computer program product | |
| WO2021082692A1 (en) | Pedestrian picture labeling method and device, storage medium, and intelligent apparatus | |
| CN108108711B (en) | Face control method, electronic device and storage medium | |
| CN110852311A (en) | Three-dimensional human hand key point positioning method and device | |
| WO2021184847A1 (en) | Method and device for shielded license plate character recognition, storage medium, and smart device | |
| CN113011403B (en) | Gesture recognition method, system, medium and device | |
| CN106096043A (en) | A kind of photographic method and mobile terminal | |
| CN107622497A (en) | Image cropping method, apparatus, computer-readable recording medium and computer equipment | |
| CN111597910A (en) | Face recognition method, face recognition device, terminal equipment and medium | |
| CN112802081A (en) | Depth detection method and device, electronic equipment and storage medium | |
| CN111259757A (en) | Image-based living body identification method, device and equipment | |
| CN111738080A (en) | Face detection and alignment method and device | |
| CN112991555B (en) | Data display method, device, equipment and storage medium | |
| WO2022199395A1 (en) | Facial liveness detection method, terminal device and computer-readable storage medium | |
| TWI657378B (en) | Method and system for object tracking in multiple non-linear distortion lenses |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180330 |