CN108564018A - A kind of biological characteristic 3D 4 D datas recognition methods and system based on infrared photography - Google Patents
A kind of biological characteristic 3D 4 D datas recognition methods and system based on infrared photography Download PDFInfo
- Publication number
- CN108564018A CN108564018A CN201810302353.5A CN201810302353A CN108564018A CN 108564018 A CN108564018 A CN 108564018A CN 201810302353 A CN201810302353 A CN 201810302353A CN 108564018 A CN108564018 A CN 108564018A
- Authority
- CN
- China
- Prior art keywords
- target organism
- image
- data
- infrared
- organism
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- 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
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
Abstract
The biological characteristic 3D 4 D datas recognition methods and system that the present invention provides a kind of based on infrared photography, 2D coloured images collected to target organism to one or more zoom color camera and depth infrared camera pre-process the collected infrared image of target organism, obtain spatial point cloud information of the target organism within given time, 3D data of the target organism within given time are obtained after registration fusion, complete model reconstruction.Database is formed using the identity information of organism as distinguishing mark;The biological characteristic 3D 4 D datas stored in database are found using the identity information of target organism, and point cloud is compared to identify the identity of target organism accordingly.It is that the 2D high clear colorfuls picture of color camera and the collected depth 3D information of depth infrared camera are subjected to registration fusion in the present invention, to reduce the extraction of characteristic point, reduces the complexity of algorithm, improve the precision and efficiency of reconstruction.
Description
Technical field
The present invention relates to biometrics identification technology field, especially a kind of biological characteristic 3D based on infrared photography is four-dimensional
Data identification method and system.
Background technology
Biological characteristic is the intrinsic physiology or behavioural characteristic of biology, such as fingerprint, palmmprint, iris or face.Biological characteristic
There are certain uniqueness and stability, i.e., the diversity ratio between certain biological characteristic of any two biology is larger, and biological characteristic
It will not generally change a lot with the time, this allows for biological characteristic and is well suited for applying in authentication or identifying system
In the scenes such as authentication information in.
In current binocular scheme, the method for registering for generally using basic gray scale, changing domain and essential characteristic, first
Feature extraction is carried out to two width or multiple image, obtains the characteristic point of image, then by carrying out similarity measurement to characteristic point
Find matched characteristic point pair;Then by matched characteristic point to the coordinate conversion parameter between obtaining a few width images;Finally
Complete image matching, method for registering of this method for registering images based on half-tone information, the method for registering based on transform domain and
The method for registering of feature based, mainly has the disadvantage that:
1) when the characteristic point unobvious or low resolution ratio in image, it is difficult to extract characteristic point from image.
2) when scene is close, the coordinate correspondence relationship of two images is not linear, is had using nonlinear transformation very big
Limitation.
3) characteristic point is found from image, further carries out characteristic matching, the calculation of large amount of complex is needed in whole process
Method, also, resolution ratio is higher, it is desirable that precision is higher, then calculate it is more complicated, it is in addition final therefore, it is necessary to high calculated performance
Result of calculation is simultaneously unstable.
Therefore, there is an urgent need for being directed to biological characteristic to carry out multidimensional data identification, safety is improved, and branch is provided for subsequent application
Support.
Invention content
In view of the above problems, it is proposed that the present invention overcoming the above problem in order to provide one kind or solves at least partly
State biological characteristic 3D 4 D datas recognition methods based on infrared photography and the system of problem.
A kind of biological characteristic 3D 4 D data recognition methods based on infrared photography comprising following steps:
S01. biological information is acquired,
Using several biometric images of infrared camera and color camera acquisition organism within given time, according to institute
Four dimension modules for stating several biometric images structure biological characteristic, to realize the biological characteristic 3D 4 D datas of the organism
Acquisition;
S02. biological characteristic 4 D data is stored,
Scanning or typing with the identity information (I1, I2 ... In) of organism, using the identity information (I1, I2 ... In) as
Distinguishing mark is associated storage to collected biological characteristic 3D 4 D datas, and formation includes a plurality of tetra- dimensions of biological characteristic 3D
According to the database of (D1, D2 ... Dn);
S03. the identification of target organism,
Acquire the biological characteristic 3D 4 D datas (T1, T2 ... Tn) of target organism, and target life described in scanning or typing
The identity information (I1, I2 ... In) of object finds the data by the identity information (I1, I2 ... In) of the target organism
The biological characteristic 3D 4 D datas (D1, D2 ... Dn) stored in library, by the biological characteristic 3D 4 D datas of the target organism
(T1, T2 ... Tn) is compared with the biological characteristic 3D 4 D datas (D1, D2 ... Dn) stored in the corresponding database respectively
It is right, to identify the identity of target organism.
Further, step S01 further includes:
The color camera is zoom color camera, to the collected 2D coloured images of one or more zoom color camera
It is pre-processed, obtains the 2D high clear colorful pictures of target organism;
The collected infrared image of depth infrared camera is pre-processed, the depth infrared of the target organism is obtained
Data, wherein the depth infrared data include the depth dimensions data of the target organism;
According to the depth infrared data of the target organism, obtain each composition point of the target organism to
Spatial point cloud information in fixing time;
The 2D high clear colorfuls picture is carried out being registrated fusion with the spatial point cloud information;
According to the 2D high clear colorfuls picture and the spatial point cloud information be registrated result data that fusion obtains, with
And the calibration information of the zoom color camera and the depth infrared camera, obtain the 4 D data of the target organism.
Further, the 4 D data step for obtaining the target organism further comprises:
By the depth infrared data transmission of several target organisms to image processor GPU and central processing unit
The processing unit of CPU;The depth infrared data information of several target organisms is assigned in the block block of GPU and is carried out
Operation, and centralized dispatching and the distribution function of CPU are combined, calculate the respective characteristic point of several described biometric images.
Further, carrying out pretreatment to the 2D coloured images includes:
The 2D coloured images are split, by the image-region of the target organism in the 2D coloured images
It is split with background area;
The image-region that the target organism is obtained to segmentation carries out image enhancement processing, obtains the target organism
2D high clear colorful pictures;Wherein, described image enhancing processing includes at least one of:Automatic white balance processing, automatic exposure
Light processing, auto-focusing processing and the processing of image deformity correction.
Further, the collected infrared image of depth infrared camera is pre-processed, including:
The infrared image is split, by the image-region and the back of the body of the target organism in the infrared image
Scene area is split;
The infrared matrix abnormal pigmentary deposit on the skin information noise filtering of image-region progress to the target organism that segmentation obtains;
The 3D dimension datas of the target organism are obtained from the image-region of the filtered target organism.
Optionally, the 2D high clear colorfuls picture is carried out being registrated fusion with the spatial point cloud information, including:
According to the 3D dimension datas of each composition point in the spatial point cloud information, TOF inverse transformations are carried out, the mesh is obtained
Mark the structure light depth image of organism;
Gaussian filtering is carried out respectively to the 2D high clear colorfuls picture and the structure light depth image;
Respectively from the 2D high clear colorfuls picture and the structure light depth image after gaussian filtering described in extraction
The characteristic of target organism determines the common characteristic portion of the 2D high clear colorfuls picture and the structure light depth image
Point;
In the common characteristic part, determine that the 2D high clear colorfuls picture is corresponding with the structure light depth image
Point;
According to coordinate of the corresponding points in the 2D high clear colorfuls picture and the structure light depth image, it is based on three
Method is cutd open at angle, determines the coordinate conversion relation of the 2D high clear colorfuls picture and the structure light depth image;
According to the coordinate conversion relation, the institute in the 2D high clear colorfuls picture and the structure light depth image is completed
State the registration fusion of each characteristic of target organism.
Optionally, it is carried out being registrated the result for merging and obtaining with the spatial point cloud information according to the 2D high clear colorfuls picture
The calibration information of data and the zoom color camera and the depth infrared camera, obtains the 3D of the target organism
Data, including:
According to the 2D high clear colorfuls picture and the spatial point cloud information be registrated result data that fusion obtains, with
And the calibration information of the zoom color camera and the depth infrared camera, in each characteristic of the target organism
It is middle to choose multiple sampled points respectively, and the multiple sampled point is calculated within given time in the coordinate of three dimensions, it is based on institute
It states multiple sampled points and obtains the 4 D data of the target organism in the coordinate of three dimensions.
Optionally, after obtaining the 3D data of the target organism, the method further includes:
Four-dimensional modeling is carried out according to 3D data of the target organism within given time, and four dimension modules are sent to
Display is shown.
Optionally, the target organism includes:Head, face or the hand of human body.
Further, when the step S03 is to the identification of target organism, using temmoku point cloud matching identification method pair
The biological characteristic 3D tetra- stored in the biological characteristic 3D 4 D datas (T1, T2 ... Tn) of the target organism and the database
Dimension data (D1, D2 ... Dn) is compared;The temmoku point cloud matching identification method includes the following steps:
S301. characteristic point is fitted;
S302. curved surface entirety best fit;
S303. similarity calculation;
Further, the temmoku point cloud matching identification method comprises the following specific steps that:
Characteristic point fitting is carried out using based on spatial domain directly matched method, in the corresponding rigid region of two clouds,
It chooses three and features above point is used as fitting key point, pass through coordinate transform, directly carry out characteristic point Corresponding matching;
After characteristic point Corresponding matching, the alignment of data of the point cloud after whole curved surface best fit;
Similarity calculation is carried out using least square method.
A kind of biological characteristic 3D 4 D data identifying systems based on infrared photography, including following device:
Collecting biological feature information device, for acquiring several biometric images of organism within given time, and
Four dimension modules that biological characteristic is built according to several described biometric images, to realize the biological characteristic 3D tetra- of the organism
Dimension data acquires;
Biological characteristic 4 D data storage device, for scanning or the identity information of typing organism (I1, I2 ... In), with
The identity information (I1, I2 ... In) is associated storage as distinguishing mark to collected biological characteristic 3D 4 D datas,
Formation includes the database of a plurality of biological characteristic 3D 4 D datas (D1, D2 ... Dn);
The identity recognition device of target organism, for according to scanning or typing target organism identity information (I1,
I2 ... In) find the biological characteristic 3D 4 D datas (D1, D2 ... Dn) stored in the database, and by the target organism
Biological characteristic 3D 4 D datas (T1, T2 ... Tn) respectively with tetra- dimensions of biological characteristic 3D that are stored in the corresponding database
It is compared according to (D1, D2 ... Dn), to identify the identity of target organism.
Further, the collecting biological feature information device includes:
First preprocessing module, for being located in advance to the collected 2D coloured images of one or more zoom color camera
Reason, obtains the 2D high clear colorful pictures of target organism;
Second preprocessing module obtains described for being pre-processed to the collected infrared image of depth infrared camera
The depth infrared data of target organism, wherein the depth infrared data include the depth dimensions number of the target organism
According to;
Point cloud generation module, for the depth infrared data according to the target organism, to the target organism
It is sampled, obtains the spatial point cloud information of the target organism;
Registration module, for carrying out being registrated fusion with the spatial point cloud information to the 2D high clear colorfuls picture;
3D data acquisition modules, for be registrated melting with the spatial point cloud information according to the 2D high clear colorfuls picture
The calibration information for closing obtained result data and the zoom color camera and the depth infrared camera, obtains the mesh
3D data of the mark organism in given time.
Further, first preprocessing module in the following way pre-processes the 2D coloured images:
The 2D coloured images are split, by the image-region of the target organism in the 2D coloured images
It is split with background area;
The image-region that the target organism is obtained to segmentation carries out image enhancement processing, obtains the target organism
2D high clear colorful pictures;Wherein, described image enhancing processing includes at least one of:Automatic white balance processing, automatic exposure
Light processing, auto-focusing processing and the processing of image deformity correction.
Further, second preprocessing module is in the following way to the collected infrared image of depth infrared camera
It is pre-processed:
The infrared image is split, by the image-region and the back of the body of the target organism in the infrared image
Scene area is split;
The infrared matrix abnormal pigmentary deposit on the skin information noise filtering of image-region progress to the target organism that segmentation obtains;
The 3D dimension datas of the target organism are obtained from the image-region of the filtered target organism.
Optionally, the registration module is in the following way to the 2D high clear colorfuls picture and the spatial point cloud information
Carry out registration fusion:
According to the 3D dimension datas of each sampled point in the spatial point cloud information, TOF inverse transformations are carried out, the mesh is obtained
Mark the structure light depth image of organism;
Gaussian filtering is carried out respectively to the 2D high clear colorfuls picture and the structure light depth image;
Respectively from the 2D high clear colorfuls picture and the structure light depth image after gaussian filtering described in extraction
The characteristic of target organism is based on triangulation, determines the 2D high clear colorfuls picture and the structure optical depth
The shared image-region of image;
In the shared image-region, determine that the 2D high clear colorfuls picture is corresponding with the structure light depth image
Point;
According to coordinate of the corresponding points in the 2D high clear colorfuls picture and the structure light depth image, institute is determined
State the coordinate conversion relation of 2D high clear colorfuls picture and the structure light depth image;
According to the coordinate conversion relation, the institute in the 2D high clear colorfuls picture and the structure light depth image is completed
State the registration fusion of each characteristic of target organism.
Optionally, the 3D data acquisition modules obtain the 3D data of the target organism in the following way:
The registration result with the spatial point cloud information and the zoom colour phase according to the 2D high clear colorfuls picture
The calibration information of machine and the depth infrared camera chooses multiple adopt respectively in each characteristic of the target organism
Sampling point, and calculate the coordinate of three dimensions of the multiple sampled point within given time, based on the multiple sampled point
The coordinate of three dimensions in given time obtains the 4 D data of the target organism.
Optionally, further include:
Four-dimensional model modeling module, for being reconstructed according to 3D data of the target organism within given time,
And four dimension modules are sent to display and are shown.
The beneficial effects of the invention are as follows:Provide a kind of biological characteristic 3D 4 D data recognition methods based on infrared photography
And system first adopts target organism one or more zoom color camera in method provided in an embodiment of the present invention
The 2D coloured images and depth infrared camera collected pre-processes the collected infrared image of target organism, is then based on
It pre-processes obtained depth infrared data to be sampled, obtains spatial point cloud information of the target organism within given time, so
It carries out being registrated fusion to pre-processing obtained 2D high clear colorfuls picture and 3D point cloud information afterwards, and then is based on registration result and change
The calibration information of the camera of burnt color camera and depth infrared camera obtains the 3D data of target organism, completes target life
3D of the object within given time is rebuild.To identify that the identity information of target identifies data, it is not necessary to by the data and number of target person
It is compared one by one according to the mass data in library, improves the efficiency of matching identification, greatly improved the speed of identification, adopt
Characteristic point fitting is carried out with based on the directly matched temmoku point cloud matching identification method in spatial domain, realizes the Fast Quasi of biological characteristic point
Composition and division in a proportion pair, and then realize the identification of identity rapid authentication.The face of people and hand are combination rigid and flexible, flexible portion
Because action variation has different forms, such as expression shape change, facial muscle can change correspondingly state, and hand carries out different dynamic
Make, hand state can also change correspondingly.Therefore different 3D renderings can be formed, if being identified with individual data characteristics, can deposited
In error.Therefore several biometric images of Visible Light Camera acquisition organism within given time, according to several described lifes
Object characteristic image builds four dimension modules of biological characteristic, realizes and is acquired to the 4 D data of organism, stores and be associated with to life afterwards
The identity information of object, when whether again identify that target organism is the organism identity, even if target organism such as face
Espressiove or hand have action, and also the identity of recognizable object organism, further improves accuracy of identification.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, various other advantages and benefit are common for this field
Technical staff will become clear.Attached drawing only for the purpose of illustrating preferred embodiments, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows the biological characteristic 3D 4 D data recognition methods according to an embodiment of the invention based on infrared photography
Flow chart;
Fig. 2 shows according to biological characteristic 3D 4 D data acquisition method stream of the one embodiment of the invention based on infrared photography
Cheng Tu;
Fig. 3 shows the coordinate conversion relation according to an embodiment of the invention cutd open based on triangle between method two width figures of calculating
Schematic diagram;
Fig. 4 shows the framework according to an embodiment of the invention based on infrared head face 4 D data acquisition system
Schematic diagram;
Fig. 5 shows the module according to an embodiment of the invention based on infrared head face 4 D data acquisition system
Structural schematic diagram;
Fig. 6 shows the framework signal according to an embodiment of the invention based on infrared hand 4 D data acquisition system
Figure;
Fig. 7 shows the modular structure according to an embodiment of the invention based on infrared hand 4 D data acquisition system
Schematic diagram;And
Fig. 8 shows the structural schematic diagram according to an embodiment of the invention based on infrared 4 D data identifying system.
Specific implementation mode
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
It should be noted that the 3D 4 D datas in the present invention refer to three-dimensional space data binding time dimension data institute shape
At data, three dimensions binding time dimension refers to:Multiple same time intervals or different time intervals, different angle, no
With the data acquisition system of image or image formation situations such as orientation or different conditions.In other words:4 D data can be multiple phases
With the 3D data acquisition systems of time interval or different time intervals, different angle, different direction, different expression forms etc..Described
Head refers to all organs of human body neck (cervical vertebra) or more;Described face refers to face and ear.
In order to solve the above technical problems, an embodiment of the present invention provides a kind of, the biological characteristic 3D based on infrared photography is four-dimensional
Data identification method.Fig. 1 shows that the biological characteristic 3D 4 D datas according to an embodiment of the invention based on infrared photography are known
The flow chart of other method:
S01. biological information is acquired,
Utilize several biometric images of infrared camera and zoom color camera acquisition organism within given time, root
Four dimension modules that biological characteristic is built according to several described biometric images, to realize that the biological characteristic 3D of the organism is four-dimensional
Data acquire;
S02. biological characteristic 4 D data is stored,
Scanning or typing with the identity information (I1, I2 ... In) of organism, using the identity information (I1, I2 ... In) as
Distinguishing mark is associated storage to collected biological characteristic 3D 4 D datas, and formation includes a plurality of tetra- dimensions of biological characteristic 3D
According to the database of (D1, D2 ... Dn);
S03. the identification of target organism,
Acquire the biological characteristic 3D 4 D datas (T1, T2 ... Tn) of target organism, and target life described in scanning or typing
The identity information (I1, I2 ... In) of object finds the data by the identity information (I1, I2 ... In) of the target organism
The biological characteristic 3D 4 D datas (D1, D2 ... Dn) stored in library, by the biological characteristic 3D 4 D datas of the target organism
(T1, T2 ... Tn) is compared with the biological characteristic 3D 4 D datas (D1, D2 ... Dn) stored in the corresponding database respectively
It is right, to identify the identity of target organism.
Preferably, as shown in Fig. 2, step S01 acquisition biological informations can also specifically include following steps S102 extremely
Step S108.
Step S102 pre-processes the collected 2D coloured images of one or more zoom color camera, obtains mesh
Mark the 2D high clear colorful pictures of organism;
Step S104 obtains the spatial point of the target organism according to the depth infrared data of the target organism
Cloud information;
Step S106 carries out being registrated fusion to the 2D high clear colorfuls picture with the spatial point cloud information;
Step S108 be registrated the knot that fusion obtains according to the 2D high clear colorfuls picture and the spatial point cloud information
The calibration information of fruit data and the zoom color camera and the depth infrared camera obtains the target organism and exists
3D data in given time.
The embodiment of the present invention carries out the acquisition of target organism using zoom color camera and depth infrared camera, and utilization is red
The depth information of outer projection acquisition target organism, can significantly improve the acquisition precision and effect of the 3D data of target organism
Rate solves the problems, such as the 3D accuracy of data acquisition of existing target organism and inefficient;Also, due to depth infrared camera
Resolution ratio it is not high, therefore, the embodiment of the present invention coordinate zoom color camera, can to avoid the not high problem of resolution ratio, also,
Due to color camera can with zoom, can effectively to target organism carry out local focusing, more improve image
Clarity;In addition, due to being that the 2D high clear colorfuls picture of color camera and depth infrared camera is collected in the present invention
Depth 3D information carries out registration fusion, to reduce the extraction of characteristic point, reduces the complexity of algorithm, improves reconstruct
Precision and efficiency.
In the alternative embodiment of the present invention, 2D coloured images are pre-processed in above step S102, it specifically can be with
Include the following steps S1021 to step S1022.
Step S1021 is split 2D coloured images, by the image-region of the target organism in 2D coloured images with
Background area is split.In this step, 2D coloured images collected to zoom color camera are split, and target is given birth to
The image-region of object and background area are separated, follow-up only to handle the image-region of target organism, to improve
Processing speed.
Step S1022, the image-region that target organism is obtained to segmentation carry out image enhancement processing, obtain target organism
The 2D high clear colorful pictures of body;Wherein, image enhancement processing includes at least one of:Automatic white balance processing, automatic exposure
Processing, auto-focusing processing and the processing of image deformity correction.By the step, can to the coloured image of target organism into
Row enhancing, to improve the clarity and contrast of image, improves the quality of coloured image, is merged convenient for subsequent registration.
Preferably, image enhancement processing includes image processor GPU and central processor CPU, is transmitted to at image
Manage the processing unit of device GPU and central processor CPU;The image information of several biometric images is assigned to the block of GPU
Operation is carried out in block, and combines centralized dispatching and the distribution function of CPU, calculates the respective feature of several biometric images
Point.It can be seen that the embodiment of the present invention carries out biological information using infrared camera and zoom color camera control technology
Acquisition, can significantly improve the collecting efficiency of biological information.Also, the embodiment of the present invention is based on central processing unit and figure
The parallel computation of processor can efficiently realize the processing of characteristic information.
Preferably, GPU is double GPU, and every GPU has a multiple block, such as 56 block, the embodiment of the present invention to this not
It is restricted.
In the alternative embodiment of the present invention, to the collected infrared image of depth infrared camera in above step S104
It carries out pretreatment and may comprise steps of S1041- steps S1043.
Step S1041:The collected infrared image of depth infrared camera is split, the target in infrared image is given birth to
The image-region of object is split with background area.
Step S1042, the infrared matrix abnormal pigmentary deposit on the skin information noise filtering of image-region progress to the target organism that segmentation obtains.
By the way that infrared matrix abnormal pigmentary deposit on the skin information noise, the noise in infrared image can be filtered out, precision is improved, is reduced at subsequent data
Reason.
Step S1043 obtains the 3D dimension datas of target organism from the image-region of filtered target organism.
The sensor of depth infrared camera sends out modulated near infrared light, meets object back reflection, and sensor is emitted by calculating light
, to generate depth information, pass through the depth of target organism with reflection interval difference or phase difference come the distance for the target organism that converts
Information is spent, the 3D dimension datas of target organism can be obtained.
In the alternative embodiment of the present invention, in above step S106 to 2D high clear colorfuls picture and 3D point cloud information into
Row registration, can specifically include following steps S1061- steps S1066.
Step S1061 carries out TOF inverse transformations, obtains mesh according to the 3D dimension datas of each composition point in 3D point cloud information
Mark the structure light depth image of organism.
Step S1062 carries out gaussian filtering respectively to 2D high clear colorfuls picture and structure light depth image.
Step S1063, respectively from the 2D high clear colorfuls picture and the structure light depth image after gaussian filtering
The characteristic of the middle extraction target organism determines being total to for the 2D high clear colorfuls picture and the structure light depth image
There is characteristic.
Step S1064 determines that 2D high clear colorfuls picture is corresponding with structure light depth image in common characteristic part
Point.
Step S1065 cuts open method based on triangle, according to corresponding points in 2D high clear colorfuls picture and structure light depth image
Coordinate determines the coordinate conversion relation of 2D high clear colorfuls picture and structure light depth image.As shown in figure 3, method is cutd open based on triangle,
It can obtain the coordinate of the 2D high clear colorfuls picture and the structure light depth image of depth infrared camera of the acquisition of zoom color camera
Transformation relation.
Step S1066 completes the target in 2D high clear colorfuls picture and structure light depth image according to coordinate conversion relation
The registration of each characteristic of organism merges.
In above-mentioned steps S1063, different characteristics can be extracted, for example, such as according to different target organisms
Fruit target organism is the hand of human body, then characteristic can be fingerprint lines, if target organism is the face of human body,
Then characteristic can be five lines of outline seen of people on the face, and the specific embodiment of the present invention is not construed as limiting.
S1061- steps S1066 through the above steps can carry out 2D high clear colorfuls picture and structure light depth image
Registration fusion, obtains the 3D information of target organism, including but not limited to:The spatial form characteristic of target organism, table
Face textural characteristics data, Facing material and light characteristic etc..
In the alternative embodiment of the present invention, according to the 2D high clear colorfuls picture and the sky in above step S108
Between point cloud information carry out the registration obtained result data of fusion and the zoom color camera and the depth infrared camera
Calibration information can be according to the 2D high clear colorfuls picture and the spatial point when obtaining the 3D data of the target organism
Cloud information carries out the calibration of result data and the zoom color camera and the depth infrared camera that registration fusion obtains
Information chooses multiple sampled points in each characteristic of the target organism, and calculates the multiple sampled point respectively
In the coordinate of three dimensions, the 3D numbers of the target organism are obtained in the coordinate of three dimensions based on the multiple sampled point
According to.In the alternative embodiment, sampled point can be with the key point of selection target organism, for example, on the profile of characteristic
Key point etc. can specifically be determined according to target organism, is not construed as limiting in the embodiment of the present invention.
In the alternative embodiment of the present invention, after step S108, target organism can also be modeled, because
This, after step S108, this method can also include:It is carried out according to 3D data of the target organism within given time
Modeling, and this four dimension module is sent to display and is shown.It, can be by collected target organism by the alternative embodiment
3D data within given time carry out four-dimensional modeling, obtain four dimension modules of target organism, and by the model visualization, make
User can easily detect whether collected data accurate, and can aspect this model is applied in other sides
Face.
In the alternative embodiment of the present invention, target organism includes but not limited to:The head of human body, face, iris or
Hand.
In the alternative embodiment of the present invention, it can be directed to different target organisms, different systems pair can be built
Target organism is acquired.For example, in the case of the head and face that target organism is human body, may be used such as Fig. 4
It is acquired with acquisition system shown in fig. 5.
As shown in Figure 4 and Figure 5, should include mainly based on infrared head, face, iris 4 D data acquisition system:In
Entreat processing module 301, depth infrared camera 302, zoom color camera 303, light module 304, camera rotating mechanism 305, people
Body-sensing is answered measurement module 306, camera data transmission module 307, display interface 308, operation interface 309, understructure 310, is adjusted
Save seat 311 and power module 312.
Wherein, as shown in Figure 4 and Figure 5, human body sensing measurement module 306 is fixed on understructure 310, display interface
308 and operation interface 309 connect with understructure 310, central processing module 301 is fixed on inside understructure 310, camera number
It is located inside understructure 310 according to transmission module 307, understructure 310 is connect with camera rotating mechanism 305, camera whirler
Structure 305 connects zoom color camera 303, depth infrared camera 302 and light module 304.
Camera rotating mechanism 305 can include but is not limited to adjustable angle camera fixed frame and tumbler, and rotate
Device may include servo motor, with fast case and transmission device.Zoom color camera 303, depth infrared camera 302, light mould
Group 304 is fixed on the adjustable angle fixed frame of camera rotating mechanism 305, and adjustable angle fixed frame is fixed on camera rotation
On the tumbler of mechanism 305.The rotation dress of the camera rotating module connection camera rotating mechanism 305 of central processing module 301
The servo motor set, is worked by control servomotor, to drive with fast case and transmission operation, and then drives rotation dress
Rotation is set, finally so that adjustable angle camera fixed frame rotates, and then reaches adjustment zoom color camera 303 and depth infrared
The purpose of the angle of camera 302.
It adjusts seat 311 and is fixed on understructure 310, adjust about 311 adjustable height of seat and the rotatable angle in left and right
Degree, adjust seat 311 include horizontally rotate servo motor, vertical lift servo motor, it is horizontal with fast case, horizontally rotate gear,
It is vertically moved up or down transmission gear screw rod and body weight inductor, wherein the chair control module connection of central processing module 301 is adjusted
Seat 311 is saved, about 311 seat adjustment height is controlled to adjust or rotates left and right angle.
Wherein, as shown in figure 5, central processing module 301 may include image quality processing chip 3011, at infrared distance measurement
It is aobvious to manage chip 3012, point cloud generation unit 3013,3D registration Algorithms processing module 3014,3D Data Synthesis module 3015, video
Show module 3016, microprocessor control module 3017, chair control module 3018, camera rotation control module 3019 and light control
Molding block 3010.
Wherein, central processing module 301 can pass through Camera Link high-speed datas with camera data transmission module 307
Line connects;Depth infrared camera 302 can be connect with camera data transmission module 307 by 3.0 data line of high speed USB;It is colored
Infrared camera can be connect with camera data transmission module 307 by MIPI high speed data lines;The control of light module 304 and phase
Machine data transmission module 307 can be connected by RS232 serial port data lines;The rotating module of camera rotating mechanism 305 and center
Camera rotation control module 3019 in processing module 301 is connected by I2C serial port data lines;Human body sensing measurement module 306
Control section connect by tri- line serial port data lines of SPI with the microprocessor control module 3017 of central processing module 301;It adjusts
The control section for saving seat 311 and the microprocessor control module 3017 of central processing module 301 pass through RS232 serial port data lines
Connection;The data transmit-receive part of display interface 308 passes through high definition HDMI with the video display module 3016 of central processing module 301
Data line connects;The data transmit-receive part of operation interface 309 is logical with the microprocessor control module 3017 of central processing module 301
Cross the connection of I2C data lines.
In one embodiment of the invention, image quality processing chip 3011 is mainly used for exporting camera transmission module
Picture color saturation adjustment, noise filtering and distortion correction etc..Infrared distance measurement processing chip 3012 mainly for the treatment of
The distance matrix information of infrared image, filtering noise reduction and deep conversion etc..Data after the processing of image quality processing chip 3011
With data fusion after the processing of infrared distance measurement processing chip 3012 mould is handled to 3D registration Algorithms processing module 3014,3D registration Algorithms
Block 3014 cuts open method and gaussian filtering method etc. by triangle and carries out registration fusion to two class data, the 3D for finally obtaining registration fusion
Data are output to 3D Data Synthesis module 3015 and carry out 3D modeling, and the 3D data that 3D modeling obtains are output to video display module
3016 show.
It in an alternate embodiment of the present invention where, can be first zoom color camera 303 and depth infrared camera 302
Lens optical is centrally located in 0 degree of state of level, and the light source center and zoom color camera 303 and depth of light module 304 are red
The lens optical centralized positioning of outer camera 302 is in together on vertical line, and wherein 305 rotational angle of camera rotating mechanism can be 0-
180 degree, speed can be that 5cm-48cm is per second, wherein the speed ratio of matching with fast case can be 300:1 (servo motor:Turning gear
Wheel).
In an alternate embodiment of the present invention where, horizontal turn servo motor, level with fast case and horizontally rotate gear
Seat horizontal rotational structure is formed, chair vertical lifting is by servo motor and vertical lift transmission gear screw rod control, wherein seat
The speed of chair vertical lift can be that 10cm-30cm is per second, and the speed of horizontal rotation can be per second with 15cm-35cm, and level is with speed
Case matches speed ratio 200:1 (motor speed:Horizontally rotate gear rotational speed).
When specifically used, it can be executed with 1- steps 11 according to the following steps.
Step 1, start setting:After startup, the input equipment relevant parameter on display interface 308, including the weight of people and
Height, colour of skin setting, the colour temperature and luminance parameter of Auto-matching light, operating mode:Automatic operation mode and manual work mould
Formula.
Step 2, whether in place human body sensing measurement module 306 detects people, and measures the height value of people's sitting posture, and zoom is colored
Camera 303 detects face automatically, judges the angle value that people sits.
Step 3, seat is adjusted:According to the present level value and angle value of people's sitting posture, adjusts seat and be automatically adjusted to face
It is suitble to zoom color camera 303 to take pictures the state scanned with depth infrared camera 302.
Step 4, zoom color camera 303 is according to face size, control camera lens automatic telescopic to suitable visual angle and clearly
Clear degree.
Step 5, for light module 304 according to the colour of skin and ambient light of face, the brightness of adjust automatically light and colour temperature make change
Burnt color camera 303 and depth infrared camera 302 collect the picture of high-resolution and high contrast.
Step 6, after the sitting posture of people reaches suitable position and light Matching and modification, depth infrared camera 302 is in face side
Position starts to collect depth distance information.
Step 7, from a side position of face start-up operation after, camera rotating mechanism 305 with fixed speed rotate and simultaneously
Camera picture and Range finder data are transmitted at the image quality processing chip 3011 and infrared distance measurement of central processing module 301
Manage chip 3012.
Step 8, infrared Range finder data transmission generates 3D to the point cloud generation unit 3013 of central processing module 301
Point cloud information.
Step 9, the high definition picture combination 3D point cloud information input of zoom color camera 303 is to 3D registration Algorithm processing modules
3014,3D registration Algorithm processing modules 3014 carry out registration fusion calculation and obtain registration fused data.
Step 10, registration fused data is input to 3D Data Synthesis module 3015,3D Data Synthesis module 3015 according to
Quasi- fused data generates 3D data models.
Step 11, after 3D data models generate, 3D data models are input to display interface 308 by video display module 3016
Upper display, and the 3D data models of display can be operated by operation interface 309.
In the alternative embodiment of the present invention, hand can also be directed to and build the 3D numbers that corresponding acquisition information carries out hand
According to acquisition.Fig. 5 is the configuration diagram based on infrared hand 3D data collecting systems, and Fig. 6 is based on infrared hand 3D numbers
It, as shown in Figure 5 and Figure 6, should be main based on infrared hand 3D data collecting systems according to the modular structure schematic diagram of acquisition system
Including:Central processing module 501, depth infrared camera 502, zoom color camera 503, light module 504, rotating mechanism 505,
Runing rest 510, hand model support construction 506, display operation module 511, hand fixed model 507, cabinet 508 and power supply
Module 509.
In the alternative embodiment, as shown in Figure 6 and Figure 7, hand model support construction 506 is fixed on cabinet 508, hand
Portion's fixed model 507 is fixed in hand model support construction 506, and display operation module 511 is fixed on cabinet 508, center
Processing module 501 is fixed on the inside of cabinet 508, and rotating mechanism 505 is fixed on the inside of cabinet 508, and runing rest 510 is fixed
On rotating mechanism 505, depth infrared camera 502, zoom color camera 503 and light module 504 are fixed on runing rest 510
On.
In an alternate embodiment of the present invention where, as shown in fig. 7, central processing module 501 includes image quality processing
Chip 5010, infrared distance measurement processing chip 5011, point cloud generation unit 5012,3D registration Algorithms processing module 5013,3D data
Synthesis module 5014, video display module 5015, microprocessor control module 5016, camera rotation control module 5017 and light
Control module 5018.
In an alternate embodiment of the present invention where, depth infrared camera 502 can pass through height with central processing module 501
Fast USB3.0 data lines connection;Zoom color camera 503 can be connected with central processing module 501 by MIPI high speed data lines
It connects;The control section of light module 504 can pass through with the camera rotation control module 5017 in central processing module 501
RS232 serial port data lines connect;The control section of rotating mechanism 505 and the camera rotation control mould in central processing module 501
Block 5017 can be connected by I2C serial port data lines;The data display unit and central processing module of display operation module 511
501 video display module 5015 is connected by high definition HDMI data lines;The data control section of display operation module 511 is in
The microprocessor control module 5016 of centre processing module 501 is connected by I2C data lines.
In the optional embodiment of the present invention, structure light mode may be used in depth infrared camera 502, is differentiating
Increase by 503 combination of zoom color camera in terms of rate, to be conducive to improve precision, resist strong light aspect, power consumption, resolution ratio,
Parameter advantage in terms of frame speed and volume.
In an alternate embodiment of the present invention where, image quality processing chip 5010 includes automatic white balance for handling
AWB, automatic exposure AE, auto-focusing AF and image deformity correction etc..
In an alternate embodiment of the present invention where, infrared distance measurement processing chip 5011 includes infrared matrix abnormal pigmentary deposit on the skin for handling
The filtering of information noise, the 3D dimension datas for obtaining target organism and point cloud information etc..
In an alternate embodiment of the present invention where, zoom color camera 503, depth infrared camera 502 and light module
504 are fixed on the rotating mechanism 505 of adjustable angle, first the camera lens of zoom color camera 503 and depth infrared camera 502
Optical centre is located in 0 degree of state of level, light source center and the zoom color camera 503 and depth infrared phase of light module 504
The lens optical centralized positioning of machine 502 is in together on vertical line.Optionally, the rotational angle of rotating mechanism 505 could be provided as
0-175 degree, speed could be provided as that 6cm-30m is per second, could be provided as 200 with speed ratio with fast case:1 (servo motor:Rotation
Gear).The focal range of zoom color camera 503 could be provided as f=4.5~108mm, the image of zoom color camera 503
The resolution ratio of sensor could be provided as 16,000,000 pixels, Aperture Range F=3.0~6.9, in addition, according to the size of finger, most
Nearly focal distance could be provided as 10cm, accurately to focus to finger.
In an alternate embodiment of the present invention where, depth infrared camera 502 could be provided as:Resolution ratio is
1920x1080, frame per second 30fps, measurement distance 0.2-4m, power consumption 1W.Certainly, however it is not limited to this, in practical applications,
It can also use above-mentioned parameter that other values, the specific present invention can also be used to be not construed as limiting.
It in a particular application, can be with using the above-mentioned 3D data for acquiring fingerprint based on infrared hand 3D data collecting systems
Include the following steps 1-11.
Step 1, start setting:After startup, the input equipment relevant parameter in display operation module 511, may include but
It is not limited to the colour temperature and luminance parameter of the weight of people and the light module 504 of height, colour of skin setting and Auto-matching.
Step 2, it after finger is put into model, is automatically adjusted to finger and zoom color camera 503 is suitble to take pictures and depth infrared
The state that camera 502 scans.
Step 4, zoom color camera 503 is according to finger size, camera lens automatic telescopic to suitable visual angle and clarity.
Step 5, adjustment light module 504:According to the colour of skin and ambient light of finger, the 504 adjust automatically brightness of light module
And colour temperature, so that zoom color camera 503 and depth infrared camera 502 can collect the picture of high-resolution and high contrast.
Step 6, depth infrared camera 502 starts to collect depth distance information in the first finger side position, successively to the
Ten fingers.
Step 7, after the start-up operation of a side position of finger, rotating mechanism 505 is rotated with fixed speed, and simultaneous transmission
The image quality processing chip 5010 and infrared distance measurement of camera picture and Range finder data to central processing module 501 handle core
Piece 5011 is acquired to the tenth finger successively.
It step 8, will be for the point cloud generation unit of the data of the depth infrared of each finger to central processing module 501
5012, point cloud generation unit 5012 generates 3D point cloud information according to the depth infrared data of each finger.
Step 9, the finger high definition picture combination 3D point cloud information input of zoom color camera 503 is handled to 3D registration Algorithms
Module 5013,3D registration Algorithms processing module 5013 carry out registration fusion calculation and obtain registration fused data.
Step 10, registration fused data is input to 3D Data Synthesis module 5014, and 3D Data Synthesis module 5014 will be registrated
Data are coordinated to generate 3D finger data models.
Step 11, after 3D finger datas model generates, 3D finger data models are transferred to aobvious by video display module 5015
Show that the display interface of operation module 511 shows and operates 3D data by operation interface.
In an alternate embodiment of the present invention where, light module 504 is adjustable color temperature and brightness, and reference color temperature can
Think that 4000-5000 (Kelvin), range of luminance values can be 20-30lux/W.
In an alternate embodiment of the present invention where, it is 40- that the parameter of zoom color camera 503, which can be horizontal field of view angle,
97 degree, vertical 45-70 degree.
In an alternate embodiment of the present invention where, structure light mode, ranging model may be used in depth infrared camera 502
Enclose 0.2m-4m, precision is +/- 0.1mm, horizontal field of view angle is 43-63 degree, vertical 25-56 degree.
In embodiments of the present invention, the dimension of time is added in the biological characteristic of 3D, constitutes four-dimensional biological characteristic, completely
The various features for restoring biology, unlimited possibility is provided for the application of subsequent biological attribute data.
May include the space shape for describing four dimension modules on different time in four dimension modules of the biological characteristic of structure
Shape characteristic, surface texture feature data of four dimension modules of description on different time, four dimension modules of description are in different time
On Facing material and 4 D datas, the embodiment of the present invention such as light characteristic this is not restricted.
In embodiments of the present invention, in step S02, the collected biological characteristic 3D 4 D datas of storing step S01 institutes,
And collected biological characteristic 3D 4 D datas are deposited using the identity information of organism (I1, I2 ... In) as distinguishing mark
Storage, formation include the database of a plurality of biological characteristic 3D 4 D datas (D1, D2 ... Dn), such as:4 D data D1 and the biology
The identity information I1 of body is associated storage, and the 4 D data D2 of another organism and the identity information I2 of the organism are closed
Connection storage, and so on, formation includes the database of n organism 4 D data.
Wherein, when acquisition target, that is, organism is human body, then identity information I includes but not limited to people's:Name, property
, not one or more in age and certificate number, certificate number may include people in life commonly used such as identification card number,
It is one or more in passport No., license number, social security number or officer's identity card number.
Preferably, the identity information is obtained by scanning identity card, passport, driving license, social security card or officer's identity card, alternatively,
Manually or automatically the mode of typing obtains identity information from identity card, passport, driving license, social security card or officer's identity card.
Preferably, in identifications of the step S03 to target organism, using temmoku point cloud matching identification method to target
The life stored in the biological characteristic 3D 4 D datas (T1, T2 ... Tn) and database of organism (organism of identity i.e. to be identified)
Object feature 3D 4 D datas (D1, D2 ... Dn) are compared, to identify the identity of target organism.First, by inputting target
The identity information of organism can be quickly found out have stored in database with the identity in this way such as the identification card number of human body
Card number be filename a 4 D data (D1, D2 ... Dn), without the mass data in the data and database by target person into
Row compares one by one, improves the efficiency of matching identification, greatly improves the speed of identification, then again current collected
The 4 D data (T1, T2 ... Tn) of the human body is compared with the 4 D data taken out in data, finally identifies the human body
Identity whether meet, and then realize authentication, specifically, being included the following steps using temmoku point cloud matching identification method:
S301. characteristic point is fitted;
S302. curved surface entirety best fit;
S303. similarity calculation.
Preferably, temmoku point cloud matching identification method further includes following specific steps:
Characteristic point fitting is carried out using based on spatial domain directly matched method, in the corresponding rigid region of two clouds,
It chooses three and features above point is used as fitting key point, pass through coordinate transform, directly carry out characteristic point Corresponding matching;
After characteristic point Corresponding matching, the alignment of data of the point cloud after whole curved surface best fit;
Similarity calculation is carried out using least square method.
Temmoku point cloud matching identification method (Yare Eyes point cloud match recognition method) is known
Other process and operation principle are as follows:First, point cloud at a time is the basic element for forming four dimension modules, it includes space
Coordinate information (XYZ) and colouring information (RGB).The attribute of point cloud includes spatial resolution, positional accuracy, surface normal etc..
Its feature is not influenced by external condition, will not all be changed for translating and rotating.Reverse software can carry out a cloud
Editor and processing, such as:Imageware, geomagic, catia, copycad and rapidform etc..Temmoku point cloud, which compares, to be known
Other method is distinctive to include based on the directly matched method in spatial domain:Iteration closest approach method ICP (Iterative closest
Point), ICP methods are generally divided into two steps, the fitting of first step characteristic point, second step curved surface entirety best fit.First fitting alignment
The purpose of characteristic point is in order to which the shortest time is found and is aligned two clouds of fitting to be compared.But not limited to this.Such as it can be with
It is:
The first step chooses three and features above point is used as fitting key point in the corresponding rigid region of two clouds,
By coordinate transform, characteristic point Corresponding matching is directly carried out.
ICP is a very effective tool in 3D data reconstruction process, at certain for curve or the registration of curved surface segment
One moment gave the rough initial alignment condition of two 3D models, and ICP iteratively seeks rigid transformation between the two with minimum
Change alignment error, realizes the registration of the space geometry relationship of the two.
Given setWithSet element indicates two model surfaces
Coordinate points, the iterative solution of ICP registration techniques apart from nearest corresponding points, establish transformation matrix, and implement to become to one of
It changes, until reaching some condition of convergence, its coding of iteration stopping is as follows:
1.1 ICP algorithm
Input .P1, P2.
P after output is transformed2
P2(0)=P2, l=0;
Do
For P2(l) each point in
In P1In look for a nearest point yi;
End For
It calculatesRegistration error E;
IfE is more than a certain threshold value
Calculate P2(l) the transformation matrix T (l) between Y (l);
P2(l+1)=T (l) P2(l), l=l+1;
Else
Stop;
End If
While||P2(l+l)-P2(l)||>threshold;
Wherein registration error
1.2 matchings based on local feature region:
By taking the identification of human face's information as an example, faceform is broadly divided into rigid model part and plasticity model part, plasticity
The accuracy of deformation effect alignment, and then influence similarity.Second of gathered data has local difference to plasticity model for the first time,
A kind of solution route be only in rigid region selected characteristic point, characteristic point be extracted from an object, under certain condition
Constant attribute is stablized in holding, and alignment is fitted using common method iteration closest approach method ICP characteristic points.
Extraction face is by the smaller region of expression influence first, such as nasal area nose, eye outer frame angle, forehead region, cheekbone
Bone region, ear region etc..Human hands finger joint is rigid region, and metacarpus is plastic region, in finger portion region selected characteristic point
It is best.Iris is rigid model.
Requirement to characteristic point:
1) completeness contains object information as much as possible, is allowed to be different from the object of other classifications;2) compactedness tables
It is as few as possible up to required data volume;3) feature is also required preferably to be remained unchanged under model rotation, translation, mirror transformation.
In 3D living things feature recognitions, using two 3D biological characteristic model point clouds of alignment, the similar of input model is calculated
Degree, wherein registration error is as difference measure.
Second step:After characteristic point best fit, the alignment of data of the point cloud after whole curved surface best fit.
Third walks, similarity calculation.Least square method
Least square method (also known as least squares method) is a kind of mathematical optimization techniques.It by minimize error quadratic sum
Find the optimal function matching of data.Unknown data can be easily acquired using least square method, and these are acquired
Data and real data between error quadratic sum be minimum.Least square method can also be used for curve matching.It is some other excellent
Change problem can also be expressed by minimizing energy or maximizing entropy with least square method.It is usually used in solving curve fit problem,
And then solve the complete fitting of curved surface.It can accelerate Data Convergence by iterative algorithm, quickly acquire optimal solution.
If 3D data models at a time are inputted with stl file format, pass through calculating point cloud and triangle
The distance of piece determines its deviation.Therefore, this method needs to establish plane equation to each tri patch, and deviation arrives flat for point
The distance in face.And be IGES or STEP models for 3D data models at a time, since free form surface expression-form is
The faces NURBS, so the distance calculating in point to face needs the method for using numerical optimization to be calculated.By in iterative calculation point cloud
Each point expresses deviation to the minimum range of nurbs surface, or that nurbs surface carried out specified scale is discrete, with point and point
Apart from approximate expression point deviation, or it is converted into STL formats and carries out deviation calculating.Different coordinate alignment and deviation calculating side
The testing result of method, acquisition is also different.The size of alignment error will directly affect the confidence level of accuracy of detection and assessment report.
Best fit alignment is that detection error averagely arrives entirety, is terminated in terms of iteration by ensureing the whole minimum condition of deviation
The alignment procedure of calculation carries out 3D analyses to registration result, generates result object in the form of the root mean square of error between two figures
Output, root mean square is bigger, and difference of two models of reflection at this is bigger.Vice versa.Judge according to registration ratio is compared
Whether it is to compare subject matter.
The biological characteristic 3D 4 D data identifying systems based on infrared photography that the present invention also provides a kind of comprising following dress
It sets:
Collecting biological feature information device, for acquiring several biometric images of organism within given time, and
Four dimension modules that biological characteristic is built according to several described biometric images, to realize the biological characteristic 3D tetra- of the organism
Dimension data acquires;
Biological characteristic 4 D data storage device, for scanning or the identity information of typing organism (I1, I2 ... In), with
The identity information (I1, I2 ... In) is associated storage as distinguishing mark to collected biological characteristic 3D 4 D datas,
Formation includes the database of a plurality of biological characteristic 3D 4 D datas (D1, D2 ... Dn);
The identity recognition device of target organism, for according to scanning or typing target organism identity information (I1,
I2 ... In) find the biological characteristic 3D 4 D datas (D1, D2 ... Dn) stored in the database, and by the target organism
Biological characteristic 3D 4 D datas (T1, T2 ... Tn) respectively with tetra- dimensions of biological characteristic 3D that are stored in the corresponding database
It is compared according to (D1, D2 ... Dn), to identify the identity of target organism.
Preferably, collecting biological feature information device includes:
Image acquisition units, the camera matrix for being formed using more cameras are acquired biological information, obtain
To several biometric images;
Feature point extraction unit is extracted for handling several biometric images in several biometric images
Respective characteristic point;
It is special to generate biology for respective characteristic point in several biometric images based on extraction for point cloud generation unit
The feature point cloud data of sign;
Four-dimensional model construction unit, four dimension modules for building biological characteristic according to feature point cloud data, to realize life
The acquisition of object feature 3D 4 D datas.
It should be noted that the biological characteristic in the embodiment of the present invention is not limited to above-mentioned head, face and/or iris
And hand, it can also be without limitation including other biological feature, such as foot, the embodiment of the present invention.
Based on each embodiment offer above based on infrared 4 D data recognition methods, it is based on same inventive concept,
The embodiment of the present invention additionally provides a kind of based on infrared 4 D data identifying system.Fig. 8 is shown to be implemented according to the present invention one
The structural schematic diagram of the biological characteristic 3D 4 D data identifying systems based on infrared photography of example.As shown in figure 8, the device can be with
Including collecting biological feature information device 910, biological information storage device 920 and target organism identification 930.Its
Middle collecting biological feature information device 910 includes the first preprocessing module 110, the second preprocessing module 120, point cloud generation module
130, registration module 140 and 3D data acquisition modules 150.
Now introduce the function of each composition or device based on infrared 4 D data identification device of the embodiment of the present invention with
And the connection relation between each section:
First preprocessing module 110, for being carried out to the collected 2D coloured images of one or more zoom color camera
Pretreatment, obtains the 2D high clear colorful pictures of target organism;
Second preprocessing module 120 obtains mesh for being pre-processed to the collected infrared image of depth infrared camera
Mark the depth infrared data of organism, wherein depth infrared data include the depth dimensions data of target organism;
Point cloud generation module 130, for the depth infrared data according to target organism, to adopting for target organism
Sample obtains the spatial point cloud information of target organism;
Registration module 140 is registrated fusion for being carried out with spatial point cloud information to 2D high clear colorfuls picture;
3D data acquisition modules 150, for be registrated merging with spatial point cloud information according to 2D high clear colorfuls picture
The calibration information of the result data and zoom color camera and depth infrared camera that arrive obtains target organism to timing
Interior 3D data.
In an alternate embodiment of the present invention where, the first preprocessing module 110 can be in the following way to 2D colours
Image is pre-processed:
2D coloured images are split, by the image-region of the target organism in 2D coloured images and background area into
Row segmentation;
The image-region that target organism is obtained to segmentation carries out image enhancement processing, obtains the 2D high definitions of target organism
Color image;Wherein, image enhancement processing includes at least one of:Automatic white balance processing, automatic exposure handle, are automatic right
Coke processing and the processing of image deformity correction.
In an alternate embodiment of the present invention where, the second preprocessing module 120 is in the following way to depth infrared phase
The collected infrared image of machine is pre-processed:
Infrared image is split, the image-region of the target organism in infrared image and background area are divided
It cuts;
The infrared matrix abnormal pigmentary deposit on the skin information noise filtering of image-region progress to the target organism that segmentation obtains;
The 3D dimension datas of target organism are obtained from the image-region of filtered target organism.
In an alternate embodiment of the present invention where, registration module 140 in the following way to 2D high clear colorfuls picture with
Spatial point cloud information carries out registration fusion:
According to the 3D dimension datas of each sampled point in spatial point cloud information, TOF inverse transformations are carried out, target organism is obtained
Structure light depth image;
Gaussian filtering is carried out respectively to 2D high clear colorfuls picture and structure light depth image;
Respectively from the 2D high clear colorfuls picture after gaussian filtering and extraction target organism in structure light depth image
Characteristic is based on triangulation, determines the shared image-region of 2D high clear colorfuls picture and structure light depth image;
In shared image-region, the corresponding points of 2D high clear colorfuls picture and structure light depth image are determined;
According to coordinate of the corresponding points in 2D high clear colorfuls picture and structure light depth image, 2D high clear colorful pictures are determined
With the coordinate conversion relation of structure light depth image;
According to coordinate conversion relation, each of 2D high clear colorfuls picture and the target organism in structure light depth image is completed
The registration of a characteristic merges.
In an alternate embodiment of the present invention where, 3D data acquisition modules 150 obtain target organism in the following way
3D data of the body within given time:
According to the registration result and zoom color camera and depth infrared of 2D high clear colorfuls picture and spatial point cloud information
The calibration information of camera chooses multiple sampled points in each characteristic of target organism, and calculates multiple samplings respectively
Point obtains the 3D data of target organism based on multiple sampled points in the coordinate of three dimensions in the coordinate of three dimensions.
In an alternate embodiment of the present invention where, further include:Modeling module is used for according to target organism to timing
Interior 3D data are modeled, and four dimension module is sent to display and is shown.
Biological attribute data storage device 920 acquires biological characteristic 3D 4 D datas (T1, T2 ... of target organism
Tn), the biological characteristic 3D tetra- stored in the database is found using the identity information of the target organism (I1, I2 ... In)
Dimension data (D1, D2 ... Dn).
The identification 930 of target organism, by biological characteristic 3D 4 D datas (T1, T2 ... of the target organism
Tn it) is compared respectively with the biological characteristic 3D 4 D datas (D1, D2 ... Dn) stored in the corresponding database, with identification
The identity of target organism.
According to the combination of any one above-mentioned alternative embodiment or multiple alternative embodiments, the embodiment of the present invention can reach
Following advantageous effect:
The recognition methods of 3D 4 D datas and device that an embodiment of the present invention provides a kind of based on infrared photography, in the present invention
In the method that embodiment provides, 2D coloured images collected to target organism to one or more zoom color camera first
The collected infrared image of target organism is pre-processed with depth infrared camera, is then based on the depth that pretreatment obtains
Infrared data is sampled, and spatial point cloud information of the target organism within given time is obtained, and is then obtained to pretreatment
2D high clear colorfuls picture carries out being registrated fusion with space cloud information, and then based on registration result and zoom color camera and depth
The calibration information of the camera of infrared camera obtains 3D data of the target organism within given time, completes target organism
Model reconstruction.Simultaneously using target organism identity information as mark to collected biological characteristic 3D 4 D datas into
Row associated storage, formation include the database of a plurality of biological characteristic 3D 4 D datas.Target biometric data is acquired again, profit
The biological characteristic 3D 4 D datas stored in database are found with the identity information of the target organism, by the target organism
The biological characteristic 3D 4 D datas of body are compared with the biological characteristic 3D 4 D datas stored in the corresponding database respectively
It is right, to identify the identity of target organism.It can thus be seen that due to being by the two-dimentional high clear colorful of color camera in the present invention
Picture and the collected depth 3D information of depth infrared camera carry out registration fusion, to reduce the extraction of characteristic point, reduce
The complexity of algorithm, improves the precision and efficiency of reconstruction.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention:It is i.e. required to protect
Shield the present invention claims the more features of feature than being expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific implementation mode are expressly incorporated in the specific implementation mode, wherein each claim itself
All as a separate embodiment of the present invention.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference mark between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be by the same hardware branch
To embody.The use of word first, second, and third does not indicate that any sequence.These words can be explained and be run after fame
Claim.
So far, although those skilled in the art will appreciate that present invention has been shown and described in detail herein multiple shows
Example property embodiment still without departing from the spirit and scope of the present invention, still can according to the present disclosure directly
Determine or derive many other variations or modifications consistent with the principles of the invention.Therefore, the scope of the present invention is understood that and recognizes
It is set to and covers other all these variations or modifications.
Claims (10)
1. a kind of biological characteristic 3D 4 D data recognition methods based on infrared photography, which is characterized in that include the following steps:
S01. biological information is acquired,
Using several biometric images of infrared camera and color camera acquisition organism within given time, according to described more
Width biometric image builds four dimension modules of biological characteristic, to realize that the biological characteristic 3D 4 D datas of the organism are adopted
Collection;
S02. biological characteristic 4 D data is stored,
Scanning or typing are with the identity information (I1, I2 ... In) of organism, using the identity information (I1, I2 ... In) as identification
Mark is associated storage to collected biological characteristic 3D 4 D datas, and formation includes a plurality of biological characteristic 3D 4 D datas
The database of (D1, D2 ... Dn);
S03. the identification of target organism,
Acquire the biological characteristic 3D 4 D datas (T1, T2 ... Tn) of target organism, and target organism described in scanning or typing
Identity information (I1, I2 ... In), found in the database by the identity information (I1, I2 ... In) of the target organism
The biological characteristic 3D 4 D datas (D1, D2 ... Dn) of storage, by the biological characteristic 3D 4 D datas of the target organism (T1,
T2 ... Tn) it is compared respectively with the biological characteristic 3D 4 D datas (D1, D2 ... Dn) stored in the corresponding database, with
Identify the identity of target organism.
2. according to the method described in claim 1, it is characterized in that, the color camera is zoom color camera, step S01 is also
Including:
The collected 2D coloured images of one or more zoom color camera are pre-processed, the 2D high of target organism is obtained
Clear color image;
The collected infrared image of depth infrared camera is pre-processed, the depth infrared number of the target organism is obtained
According to, wherein the depth infrared data include the depth dimensions data of the target organism;
According to the depth infrared data of the target organism, obtain each composition point of the target organism to timing
Interior spatial point cloud information;
The 2D high clear colorfuls picture is carried out being registrated fusion with the spatial point cloud information;
Be registrated result data, the Yi Jisuo that fusion obtains according to the 2D high clear colorfuls picture and the spatial point cloud information
The calibration information for stating zoom color camera and the depth infrared camera, obtains the 4 D data of the target organism.
3. according to the method described in claim 2, it is characterized in that, obtaining the 4 D data step of the target organism into one
Step includes:
By the depth infrared data transmission of several target organisms to image processor GPU and central processor CPU
Processing unit;The depth infrared data information of several target organisms is assigned in the block block of GPU and is transported
It calculates, and combines centralized dispatching and the distribution function of CPU, calculate the respective characteristic point of several described biometric images.
4. according to the method described in claim 3, wherein, carrying out pretreatment to the 2D coloured images includes:
The 2D coloured images are split, by the image-region and the back of the body of the target organism in the 2D coloured images
Scene area is split;
The image-region that the target organism is obtained to segmentation carries out image enhancement processing, obtains the 2D of the target organism
High clear colorful picture;Wherein, described image enhancing processing includes at least one of:At automatic white balance processing, automatic exposure
Reason, auto-focusing processing and the processing of image deformity correction.
5. according to the method described in claim 3, wherein, pre-processed to the collected infrared image of depth infrared camera,
Including:
The infrared image is split, by the image-region and background area of the target organism in the infrared image
Domain is split;
The infrared matrix abnormal pigmentary deposit on the skin information noise filtering of image-region progress to the target organism that segmentation obtains;
The 3D dimension datas of the target organism are obtained from the image-region of the filtered target organism.
6. according to claim 2 to 5 any one of them method, wherein to the 2D high clear colorfuls picture and the spatial point
Cloud information carries out registration fusion, including:
According to the 3D dimension datas of each composition point in the spatial point cloud information, TOF inverse transformations are carried out, obtain the target life
The structure light depth image of object;
Gaussian filtering is carried out respectively to the 2D high clear colorfuls picture and the structure light depth image;
Respectively the target is extracted from the 2D high clear colorfuls picture and the structure light depth image after gaussian filtering
The characteristic of organism determines the common characteristic part of the 2D high clear colorfuls picture and the structure light depth image;
In the common characteristic part, the corresponding points of the 2D high clear colorfuls picture and the structure light depth image are determined;
According to coordinate of the corresponding points in the 2D high clear colorfuls picture and the structure light depth image, cutd open based on triangle
Method determines the coordinate conversion relation of the 2D high clear colorfuls picture and the structure light depth image;
According to the coordinate conversion relation, the mesh in the 2D high clear colorfuls picture and the structure light depth image is completed
Mark the registration fusion of each characteristic of organism.
7. according to claim 2 to 5 any one of them method, wherein according to the 2D high clear colorfuls picture and the space
Point cloud information carries out the mark of result data and the zoom color camera and the depth infrared camera that registration fusion obtains
Determine information, obtains the 3D data of the target organism, including:
Be registrated result data, the Yi Jisuo that fusion obtains according to the 2D high clear colorfuls picture and the spatial point cloud information
The calibration information for stating zoom color camera and the depth infrared camera is divided in each characteristic of the target organism
Multiple sampled points are not chosen, and calculate the multiple sampled point within given time in the coordinate of three dimensions, based on described more
A sampled point obtains the 4 D data of the target organism in the coordinate of three dimensions.
8. according to claim 2 to 5 any one of them method, wherein after obtaining the 3D data of the target organism,
The method further includes:
Four-dimensional modeling is carried out according to 3D data of the target organism within given time, and four dimension modules are sent to display
Device is shown;The target organism includes:Head, face or the hand of human body.
9. according to the method described in claim 1, it is characterized in that, when the step S03 is to the identification of target organism,
Using temmoku point cloud matching identification method to the biological characteristic 3D 4 D datas (T1, T2 ... Tn) of the target organism and the number
It is compared according to the biological characteristic 3D 4 D datas (D1, D2 ... Dn) stored in library;The temmoku point cloud matching identification method includes
Following steps:
S301. characteristic point is fitted;
S302. curved surface entirety best fit;
S303. similarity calculation;The temmoku point cloud matching identification method comprises the following specific steps that:
Characteristic point fitting is carried out using based on the directly matched method in spatial domain, in the corresponding rigid region of two clouds, is chosen
Three and features above point conduct fitting key point, pass through coordinate transform, directly carry out characteristic point Corresponding matching;
After characteristic point Corresponding matching, the alignment of data of the point cloud after whole curved surface best fit;
Similarity calculation is carried out using least square method.
10. a kind of biological characteristic 3D 4 D data identifying systems based on infrared photography, which is characterized in that including following device:
Collecting biological feature information device, for acquiring several biometric images of organism within given time, and according to
Four dimension modules of several biometric images structure biological characteristic, to realize tetra- dimensions of biological characteristic 3D of the organism
According to acquisition;
Biological characteristic 4 D data storage device, for scanning or the identity information of typing organism (I1, I2 ... In), with described
Identity information (I1, I2 ... In) is associated storage as distinguishing mark to collected biological characteristic 3D 4 D datas, is formed
Include the database of a plurality of biological characteristic 3D 4 D datas (D1, D2 ... Dn);
The identity recognition device of target organism, for identity information (I1, I2 ... according to scanning or the target organism of typing
In the biological characteristic 3D 4 D datas (D1, D2 ... Dn) stored in the database) are found, and by the life of the target organism
Object feature 3D 4 D datas (T1, T2 ... Tn) respectively with the biological characteristic 3D 4 D datas that are stored in the corresponding database
(D1, D2 ... Dn) is compared, to identify the identity of target organism;The collecting biological feature information device includes:
First preprocessing module, for being pre-processed to the collected 2D coloured images of one or more zoom color camera,
Obtain the 2D high clear colorful pictures of target organism;
Second preprocessing module obtains the target for being pre-processed to the collected infrared image of depth infrared camera
The depth infrared data of organism, wherein the depth infrared data include the depth dimensions data of the target organism;
Point cloud generation module, for the depth infrared data according to the target organism, the progress to the target organism
Sampling, obtains the spatial point cloud information of the target organism;
Registration module, for carrying out being registrated fusion with the spatial point cloud information to the 2D high clear colorfuls picture;
3D data acquisition modules, for be registrated merging with the spatial point cloud information according to the 2D high clear colorfuls picture
The calibration information of the result data and the zoom color camera and the depth infrared camera that arrive obtains the target life
3D data of the object within given time;First preprocessing module in the following way carries out the 2D coloured images pre-
Processing:
The 2D coloured images are split, by the image-region and the back of the body of the target organism in the 2D coloured images
Scene area is split;
The image-region that the target organism is obtained to segmentation carries out image enhancement processing, obtains the 2D of the target organism
High clear colorful picture;Wherein, described image enhancing processing includes at least one of:At automatic white balance processing, automatic exposure
Reason, auto-focusing processing and the processing of image deformity correction;Second preprocessing module is in the following way to depth infrared
The collected infrared image of camera is pre-processed:
The infrared image is split, by the image-region and background area of the target organism in the infrared image
Domain is split;
The infrared matrix abnormal pigmentary deposit on the skin information noise filtering of image-region progress to the target organism that segmentation obtains;
The 3D dimension datas of the target organism are obtained from the image-region of the filtered target organism;It is described to match
Quasi-mode block carries out being registrated fusion to the 2D high clear colorfuls picture with the spatial point cloud information in the following way:
According to the 3D dimension datas of each sampled point in the spatial point cloud information, TOF inverse transformations are carried out, obtain the target life
The structure light depth image of object;
Gaussian filtering is carried out respectively to the 2D high clear colorfuls picture and the structure light depth image;
Respectively the target is extracted from the 2D high clear colorfuls picture and the structure light depth image after gaussian filtering
The characteristic of organism is based on triangulation, determines the 2D high clear colorfuls picture and the structure light depth image
Shared image-region;
In the shared image-region, the corresponding points of the 2D high clear colorfuls picture and the structure light depth image are determined;
According to coordinate of the corresponding points in the 2D high clear colorfuls picture and the structure light depth image, the 2D is determined
The coordinate conversion relation of high clear colorful picture and the structure light depth image;
According to the coordinate conversion relation, the mesh in the 2D high clear colorfuls picture and the structure light depth image is completed
Mark the registration fusion of each characteristic of organism;The 3D data acquisition modules obtain the target life in the following way
The 3D data of object:
According to the registration result of the 2D high clear colorfuls picture and the spatial point cloud information and the zoom color camera and
The calibration information of the depth infrared camera chooses multiple samplings respectively in each characteristic of the target organism
Point, and the coordinate of three dimensions of the multiple sampled point within given time is calculated, based on the multiple sampled point given
The coordinate of three dimensions in time obtains the 4 D data of the target organism;Further include:Four-dimensional model modeling module is used
It is reconstructed according to 3D data of the target organism within given time, and four dimension modules is sent to display and are shown
Show.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810302353.5A CN108564018A (en) | 2018-04-04 | 2018-04-04 | A kind of biological characteristic 3D 4 D datas recognition methods and system based on infrared photography |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810302353.5A CN108564018A (en) | 2018-04-04 | 2018-04-04 | A kind of biological characteristic 3D 4 D datas recognition methods and system based on infrared photography |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108564018A true CN108564018A (en) | 2018-09-21 |
Family
ID=63534257
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810302353.5A Withdrawn CN108564018A (en) | 2018-04-04 | 2018-04-04 | A kind of biological characteristic 3D 4 D datas recognition methods and system based on infrared photography |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108564018A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109495732A (en) * | 2018-10-31 | 2019-03-19 | 昆山睿力得软件技术有限公司 | A kind of 3D imaging vision guidance system |
CN109671143A (en) * | 2018-12-23 | 2019-04-23 | 广东腾晟信息科技有限公司 | Human body intelligent modeling method |
CN110188616A (en) * | 2019-05-05 | 2019-08-30 | 盎锐(上海)信息科技有限公司 | Space modeling method and device based on 2D and 3D image |
CN110287776A (en) * | 2019-05-15 | 2019-09-27 | 北京邮电大学 | A kind of method, apparatus and computer readable storage medium of recognition of face |
CN110309782A (en) * | 2019-07-02 | 2019-10-08 | 四川大学 | It is a kind of based on infrared with visible light biocular systems living body faces detection methods |
CN110909691A (en) * | 2019-11-26 | 2020-03-24 | 腾讯科技(深圳)有限公司 | Motion detection method and device, computer readable storage medium and computer equipment |
CN111859489A (en) * | 2020-07-27 | 2020-10-30 | 深圳市纵维立方科技有限公司 | Support structure generation method and device, electronic equipment and storage medium |
CN111859577A (en) * | 2020-07-27 | 2020-10-30 | 江苏科技大学 | Direct layering method for laser additive repair |
CN113065502A (en) * | 2019-12-12 | 2021-07-02 | 天目爱视(北京)科技有限公司 | 3D information acquisition system based on standardized setting |
CN114466175A (en) * | 2022-04-08 | 2022-05-10 | 深圳市响西科技有限公司 | 3D acquisition device, 3D structured light modeling method and virtual reality all-in-one machine |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893965A (en) * | 2016-03-31 | 2016-08-24 | 中国科学院自动化研究所 | Binocular visual image synthesis device and method used for unspecified person |
CN106920274A (en) * | 2017-01-20 | 2017-07-04 | 南京开为网络科技有限公司 | Mobile terminal 2D key points rapid translating is the human face model building of 3D fusion deformations |
CN107590435A (en) * | 2017-08-09 | 2018-01-16 | 广东欧珀移动通信有限公司 | Palm grain identification method, device and terminal device |
-
2018
- 2018-04-04 CN CN201810302353.5A patent/CN108564018A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893965A (en) * | 2016-03-31 | 2016-08-24 | 中国科学院自动化研究所 | Binocular visual image synthesis device and method used for unspecified person |
CN106920274A (en) * | 2017-01-20 | 2017-07-04 | 南京开为网络科技有限公司 | Mobile terminal 2D key points rapid translating is the human face model building of 3D fusion deformations |
CN107590435A (en) * | 2017-08-09 | 2018-01-16 | 广东欧珀移动通信有限公司 | Palm grain identification method, device and terminal device |
Non-Patent Citations (1)
Title |
---|
贾保柱: "融合2D与3D图像的三维重建系统实现", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109495732A (en) * | 2018-10-31 | 2019-03-19 | 昆山睿力得软件技术有限公司 | A kind of 3D imaging vision guidance system |
CN109671143A (en) * | 2018-12-23 | 2019-04-23 | 广东腾晟信息科技有限公司 | Human body intelligent modeling method |
CN110188616A (en) * | 2019-05-05 | 2019-08-30 | 盎锐(上海)信息科技有限公司 | Space modeling method and device based on 2D and 3D image |
CN110188616B (en) * | 2019-05-05 | 2023-02-28 | 上海盎维信息技术有限公司 | Space modeling method and device based on 2D and 3D images |
CN110287776A (en) * | 2019-05-15 | 2019-09-27 | 北京邮电大学 | A kind of method, apparatus and computer readable storage medium of recognition of face |
CN110309782B (en) * | 2019-07-02 | 2022-05-03 | 四川大学 | Living body face detection method based on infrared and visible light binocular system |
CN110309782A (en) * | 2019-07-02 | 2019-10-08 | 四川大学 | It is a kind of based on infrared with visible light biocular systems living body faces detection methods |
CN110909691A (en) * | 2019-11-26 | 2020-03-24 | 腾讯科技(深圳)有限公司 | Motion detection method and device, computer readable storage medium and computer equipment |
CN110909691B (en) * | 2019-11-26 | 2023-05-05 | 腾讯科技(深圳)有限公司 | Motion detection method, motion detection device, computer-readable storage medium, and computer device |
CN113065502A (en) * | 2019-12-12 | 2021-07-02 | 天目爱视(北京)科技有限公司 | 3D information acquisition system based on standardized setting |
CN111859489A (en) * | 2020-07-27 | 2020-10-30 | 深圳市纵维立方科技有限公司 | Support structure generation method and device, electronic equipment and storage medium |
CN111859577A (en) * | 2020-07-27 | 2020-10-30 | 江苏科技大学 | Direct layering method for laser additive repair |
CN114466175A (en) * | 2022-04-08 | 2022-05-10 | 深圳市响西科技有限公司 | 3D acquisition device, 3D structured light modeling method and virtual reality all-in-one machine |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108564018A (en) | A kind of biological characteristic 3D 4 D datas recognition methods and system based on infrared photography | |
CN108470373B (en) | It is a kind of based on infrared 3D 4 D data acquisition method and device | |
KR102041906B1 (en) | API engine for discrimination of facial skin disease based on artificial intelligence that discriminates skin disease by using image captured through facial skin photographing device | |
CN109269405B (en) | A kind of quick 3D measurement and comparison method | |
US11836880B2 (en) | Adjusting a digital representation of a head region | |
CN108447017A (en) | Face virtual face-lifting method and device | |
Gupta et al. | Texas 3D face recognition database | |
US7512255B2 (en) | Multi-modal face recognition | |
CN105956515B (en) | Solid-EO-1 hyperion face identification method based on pole imaging | |
Sablatnig et al. | Hierarchical classification of paintings using face-and brush stroke models | |
CN108549873A (en) | Three-dimensional face identification method and three-dimensional face recognition system | |
Ibáñez et al. | An experimental study on the applicability of evolutionary algorithms to craniofacial superimposition in forensic identification | |
CN108765273A (en) | The virtual lift face method and apparatus that face is taken pictures | |
US20100189357A1 (en) | Method and device for the virtual simulation of a sequence of video images | |
CN108416312B (en) | A kind of biological characteristic 3D data identification method taken pictures based on visible light | |
CN109583304A (en) | A kind of quick 3D face point cloud generation method and device based on structure optical mode group | |
CN110363116A (en) | Irregular face antidote, system and medium based on GLD-GAN | |
CN108319939A (en) | A kind of 3D four-dimension head face data discrimination apparatus | |
CN106155299B (en) | A kind of pair of smart machine carries out the method and device of gesture control | |
CN108470166A (en) | A kind of biological characteristic 3D 4 D datas recognition methods and system based on laser scanning | |
CN108550184A (en) | A kind of biological characteristic 3D 4 D datas recognition methods and system based on light-field camera | |
CN102961201A (en) | Method for manufacturing personalized facial prosthesis by laser scanning and quick molding technologies | |
CN108520230A (en) | A kind of 3D four-dimension hand images data identification method and equipment | |
CN108446597B (en) | A kind of biological characteristic 3D collecting method and device based on Visible Light Camera | |
CN108334874A (en) | A kind of 3D four-dimension iris image identification equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180921 |