CN107608541A - Three-dimensional attitude positioning method, device and electronic equipment - Google Patents
Three-dimensional attitude positioning method, device and electronic equipment Download PDFInfo
- Publication number
- CN107608541A CN107608541A CN201710961392.1A CN201710961392A CN107608541A CN 107608541 A CN107608541 A CN 107608541A CN 201710961392 A CN201710961392 A CN 201710961392A CN 107608541 A CN107608541 A CN 107608541A
- Authority
- CN
- China
- Prior art keywords
- image
- flying squirrel
- ordinate
- coordinate
- cmos camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a kind of three-dimensional attitude positioning method, device and electronic equipment, it is related to field of computer technology.The three-dimensional attitude positioning method includes:Obtain the flying squirrel of the sensor measure for the flying squirrel for being internally provided with infrared diode includes attitude angle data and the first plane coordinates in multiple first position data, first position data corresponding to multiple predeterminated positions difference;The flying squirrel that binocular CMOS camera according to infrared filter is provided with gathers obtains flying squirrel in multiple second place coordinates corresponding to multiple predeterminated positions difference in the location drawing picture of the multiple predeterminated position;Multiple first position coordinates corresponding to multiple first position coordinates and multiple second place coordinates are obtained based on the first preset algorithm;Based on multiple first position coordinates and multiple attitude angle datas generation flying squirrel in second place data corresponding to multiple predeterminated positions difference.The three-dimensional attitude positioning method, device and electronic equipment can preferably get the attitude data of flying squirrel under dark condition.
Description
Technical field
The present invention relates to field of computer technology, in particular to a kind of three-dimensional attitude positioning method, device and electronics
Equipment.
Background technology
At present under dark condition, the alignment sensor in wireless air flying squirrel can obtain flying squirrel in given plane
The attitude angle data of lateral coordinates, longitudinal coordinate and three directions, and vertical coordinate can not be got, so as in dark condition
The 3 d pose location data of flying squirrel can not be got down.
The content of the invention
In view of this, the embodiments of the invention provide a kind of three-dimensional attitude positioning method, device and electronic equipment, to solve
Above mentioned problem.
To achieve these goals, the technical solution adopted by the present invention is as follows:
A kind of three-dimensional attitude positioning method, methods described include:Obtain the biography for the flying squirrel for being internally provided with infrared diode
The flying squirrel of sensor measure is in multiple first position data, the first position packet corresponding to multiple predeterminated positions difference
Include attitude angle data and the first plane coordinates;Binocular CMOS camera according to infrared filter is provided with gathers described winged
Mouse the location drawing picture of the multiple predeterminated position obtain the flying squirrel the multiple predeterminated position respectively corresponding to multiple the
One space coordinates;Multiple first plane coordinates and multiple first space coordinates pair are obtained based on the first preset algorithm
The multiple first position coordinates answered;It is described winged based on the multiple first position coordinate and multiple attitude angle data generations
Mouse is in second place data corresponding to the multiple predeterminated position difference.
A kind of 3 d pose positioner, described device include:First data acquisition module, the second data acquisition module,
Processing module and data generation module, wherein, first data acquisition module is internally provided with infrared two pole for acquisition
The flying squirrel of the sensor measure of the flying squirrel of pipe multiple predeterminated positions respectively corresponding to multiple first position data, described the
One position data includes attitude angle data and the first plane coordinates;Second data acquisition module is used for red according to being provided with
The flying squirrel of the binocular CMOS camera collection of outer filter plate obtains described fly in the location drawing picture of the multiple predeterminated position
Mouse is in multiple first space coordinates corresponding to the multiple predeterminated position difference;The processing module is used for based on the first pre- imputation
Method obtains multiple first position coordinates corresponding to multiple first plane coordinates and multiple first space coordinates;It is described
Data generation module is used to exist based on the multiple first position coordinate and multiple attitude angle data generations flying squirrel
Second place data corresponding to the multiple predeterminated position difference.
A kind of electronic equipment, the electronic equipment include memory and processor, and the memory is couple to the processing
Device, the memory store instruction, make to operate below the computing device when executed by the processor:Obtain
The flying squirrel that the sensor for the flying squirrel for being internally provided with infrared diode determines is taken more corresponding to multiple predeterminated positions difference
Individual first position data, the first position data include attitude angle data and the first plane coordinates;It is infrared according to being provided with
The flying squirrel of the binocular CMOS camera collection of filter plate obtains the flying squirrel in the location drawing picture of the multiple predeterminated position
In multiple first space coordinates corresponding to the multiple predeterminated position difference;Multiple described first is obtained based on the first preset algorithm
Multiple first position coordinates corresponding to plane coordinates and multiple first space coordinates;Sat based on the multiple first position
It is marked with and multiple attitude angle datas generates the flying squirrel in second place data corresponding to the multiple predeterminated position difference.
Three-dimensional attitude positioning method, device and electronic equipment provided in an embodiment of the present invention, it is internally provided with by obtaining
The flying squirrel of the sensor measure of the flying squirrel of infrared diode multiple predeterminated positions respectively corresponding to multiple first position data, the
One position data includes attitude angle data and the first plane coordinates;Then taken the photograph according to the binocular CMOS for being provided with infrared filter
As the flying squirrel that head gathers the location drawing picture of multiple predeterminated positions obtain flying squirrel multiple predeterminated positions respectively corresponding to multiple the
One space coordinates;Obtained again based on the first preset algorithm more corresponding to multiple first plane coordinates and multiple first space coordinates
Individual first position coordinate;It is finally based on multiple first position coordinates and multiple attitude angle datas generates flying squirrel in multiple default positions
Put second place data corresponding to difference.So as to, under dark condition, 3 d pose data corresponding to flying squirrel can be obtained, with
Solves the problems, such as the 3 d pose location data that flying squirrel can not be got under dark condition.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 shows the block diagram of electronic equipment provided in an embodiment of the present invention;
Fig. 2 shows the flow chart of three-dimensional attitude positioning method provided in an embodiment of the present invention;
Fig. 3 shows the step S120 of three-dimensional attitude positioning method provided in an embodiment of the present invention flow chart;
Fig. 4 shows the schematic diagram of preset model provided in an embodiment of the present invention;
Fig. 5 shows the step S130 of three-dimensional attitude positioning method provided in an embodiment of the present invention flow chart;
Fig. 6 shows the module map of 3 d pose positioner provided in an embodiment of the present invention;
Fig. 7 shows the module map of the processing module of 3 d pose positioner provided in an embodiment of the present invention;
Fig. 8 shows the module of the second data acquisition module of 3 d pose positioner provided in an embodiment of the present invention
Figure.
Embodiment
Below in conjunction with accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Generally exist
The component of the embodiment of the present invention described and illustrated in accompanying drawing can be configured to arrange and design with a variety of herein.Cause
This, the detailed description of the embodiments of the invention to providing in the accompanying drawings is not intended to limit claimed invention below
Scope, but it is merely representative of the selected embodiment of the present invention.Based on embodiments of the invention, those skilled in the art are not doing
The every other embodiment obtained on the premise of going out creative work, belongs to the scope of protection of the invention.
It should be noted that:Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent accompanying drawing in individual accompanying drawing.Meanwhile the present invention's
In description, term " first ", " second " etc. are only used for distinguishing description, and it is not intended that instruction or hint relative importance.
Fig. 1 shows a kind of structured flowchart for the electronic equipment that can be applied in the embodiment of the present invention.It is as shown in figure 1, electric
Sub- equipment 100 includes memory 102, storage control 104, one or more (one is only shown in figure) processors 106, peripheral hardware
Interface 108, radio-frequency module 110, audio-frequency module 112, display unit 114 etc..These components by one or more communication bus/
Signal wire 116 mutually communicates.
Memory 102 can be used for storage software program and module, such as the 3 d pose positioning side in the embodiment of the present invention
Programmed instruction/module corresponding to method and device, processor 106 by operation be stored in software program in memory 102 and
Module, so as to perform various function application and data processing, such as 3 d pose positioner provided in an embodiment of the present invention.
Memory 102 may include high speed random access memory, may also include nonvolatile memory, such as one or more magnetic
Property storage device, flash memory or other non-volatile solid state memories.Processor 106 and other possible components are to storage
The access of device 102 can be carried out under the control of storage control 104.
Various input/output devices are coupled to processor 106 and memory 102 by Peripheral Interface 108.In some implementations
In example, Peripheral Interface 108, processor 106 and storage control 104 can be realized in one single chip.In some other reality
In example, they can be realized by independent chip respectively.
Radio-frequency module 110 is used to receiving and sending electromagnetic wave, realizes the mutual conversion of electromagnetic wave and electric signal, so that with
Communication network or other equipment are communicated.
Audio-frequency module 112 provides a user COBBAIF, and it may include one or more microphones, one or more raises
Sound device and voicefrequency circuit.
Display unit 114 provides a display interface between electronic equipment 100 and user.Specifically, display unit 114
Video frequency output is shown to user, the content of these video frequency outputs may include word, figure, video and its any combination.
It is appreciated that structure shown in Fig. 1 is only to illustrate, electronic equipment 100 may also include it is more more than shown in Fig. 1 or
Less component, or there is the configuration different from shown in Fig. 1.Each component shown in Fig. 1 can use hardware, software or its
Combination is realized.
First embodiment
The flow chart of three-dimensional attitude positioning method provided in an embodiment of the present invention as shown in Figure 2.Refer to Fig. 2, the party
Method includes:
Step S110:The flying squirrel of sensor measure for the flying squirrel for being internally provided with infrared diode is obtained multiple pre-
If multiple first position data corresponding to the difference of position, the first position data include attitude angle data and the first plane is sat
Mark.
In flying squirrel motion process, the gyro sensor in flying squirrel can obtain the horizontal, longitudinal and vertical of flying squirrel
Attitude angle data, flying squirrel is in horizontal and longitudinal direction coordinate data.
In embodiments of the present invention, due to that can not obtain the 3 d pose data of flying squirrel under dark condition, therefore can be with
Infrared diode is set in the inside of flying squirrel, in order to carry out obtaining for follow-up 3 d pose data for the image for catching flying squirrel
Take.In addition, the shape of flying squirrel can be spherical.Flying squirrel can be the relative position motion of a screen, and can set multiple
Predeterminated position.And flying squirrel can be with the electronic equipment communication connection for realizing three-dimensional attitude positioning method.Multiple default positions
Multiple positions of the flying squirrel in motion process are set to, it is specifically as follows the position conduct of flying squirrel corresponding to multiple preset time points
Predeterminated position.For example, motion process of the flying squirrel within certain time, be divided into time point 1, time point 2, time point 3 etc. it is multiple when
Between the position of flying squirrel corresponding to multiple time points such as point, time point 1, time point 2, time point 3 then be flying squirrel predeterminated position.
It is thus possible to the flying squirrel of the sensor measure of flying squirrel is got multiple first corresponding to multiple predeterminated positions difference
Position data.Also, first position data include laterally, longitudinal direction, the attitude angle in vertical three directions, and transverse direction, longitudinal direction
The first plane coordinates that coordinate is formed.
Step S120:The flying squirrel that binocular CMOS camera according to infrared filter is provided with gathers is the multiple
The location drawing picture of predeterminated position obtains the flying squirrel in multiple first space coordinates corresponding to the multiple predeterminated position difference.
In embodiments of the present invention, binocular CMOS camera can be installed in the relative screen of flying squirrel, since it is desired that catching
The image of flying squirrel is caught, therefore infrared filter can be set in binocular CMOS camera.Preferably, binocular CMOS camera can be with
It is arranged at the top of screen.
So as in flying squirrel motion process, while binocular CMOS camera be controlled to collect flying squirrel position
Image.Specifically, binocular CMOS camera collection flying squirrel can be controlled in the location drawing picture of above-mentioned predeterminated position.
It is then possible to the flying squirrel gathered according to binocular CMOS camera is flown in the location drawing picture of multiple predeterminated positions
Mouse is in multiple first space coordinates corresponding to multiple predetermined positions difference.
Specifically, refer to Fig. 3, according to the flying squirrel that binocular CMOS camera gathers multiple predeterminated positions location drawing picture
Obtain flying squirrel multiple predeterminated positions respectively corresponding to multiple first space coordinates, can include:
Step S121:Obtain the first CMOS camera and the second CMOS camera difference of the binocular CMOS camera
First image and second image of the flying squirrel of collection in a predeterminated position.
Specifically, step S121 can include:First CMOS camera and the second CMOS camera is controlled to obtain
The 3rd image of the flying squirrel and the 4th image;Obtain first corresponding to the 3rd image and the 4th image difference
Frame selects image and the second frame selects image, and first frame selects image and second frame to select image corresponding to the flying squirrel
Image corresponding to frame favored area;When first CMOS camera and second CMOS camera gather respectively it is described fly
Mouse selects image and second frame to select images match with first frame respectively in the image of the predeterminated position, then by described in
The image of first CMOS camera collection is as the first image, and the image of the second CMOS camera collection is as the second figure
Picture.
It is possible, firstly, to control the first CMOS camera and the second CMOS camera gather respectively be internally provided with it is infrared by two
The 3rd image of the flying squirrel of pole pipe and the 4th image.It is thus possible to get the 3rd image and the 4th figure corresponding to flying squirrel
Picture.Then the 3rd image and the 4th image can be obtained and be transformed into figure corresponding to HIS color spaces from RGB color
Picture.Infrared diode is internally provided with due to collecting flying squirrel, and binocular CMOS camera is provided with infrared filter, therefore catch
The color that flying squirrel is presented in the image grasped is mainly red., can be in HIS color spaces pair in order to extract the feature of flying squirrel
H components are extracted in the image answered again, the value for taking H components is 0~180.It should be noted that the scope of the H components includes flying squirrel
Color gamut, may then pass through man-machine interaction and obtain flying squirrel largest square in the picture or rectangular area and be used as the
First frame corresponding to three images selects the second frame corresponding to image and the 4th image to select image.Again with built-in function meter in Opencv
Calculating first frame selects image and the second frame to select the histogram of each color in image, goes out further according to histogram calculation described
First frame selects back projection figure corresponding to image, and the second frame to select back projection figure corresponding to image.It is understood that fly
The color of mouse is the color that ratio is maximum in back projection figure, due to its spherical characteristic, therefore in back projection figure all the time
It is the spherical of white.When flying squirrel is moved, it is necessary to track its position, and determine the position where flying squirrel.
It is specifically as follows the first CMOS camera of control and gathers flying squirrel in the image of predetermined position, the second CMOS camera
Image of the flying squirrel in predetermined position is gathered, and when the image and the first frame of judging the collection of the first CMOS camera select image
Matching, the image and the second frame of the collection of the second CMOS camera select images match, then can gathered the first CMOS camera
Image is as the first image, and the image of the second CMOS camera collection is as the second image.It is understood that utilize tracking box
The position of flying squirrel is determined, tracking box is that the first frame selects image and the second frame to select corresponding framework in image, passes through meanshift
Algorithm, the barycenter of the color in tracking box is calculated, when the center of barycenter slip chart picture, then using the barycenter as new center, again
Image being gathered, when center overlaps with barycenter in the image of collection, then it represents that the position where tracking box is the position of flying squirrel, this
When, the image of tracking box and the first frame select image and the second frame to select the matching degree highest of image, i.e. color-match degree highest.From
And can obtain flying squirrel predetermined position the first CMOS camera gather the first image and the second CMOS camera adopt
Second image of collection.
Step S122:Obtain corresponding to the first back projection figure and second image corresponding to described first image the
Two back projection figures, the first back projection figure and the second back projection figure include area corresponding to the flying squirrel
Domain.
Then further according to the method for the acquisition back projection figure in step S122, the first back projection of the first image of acquisition
Figure, the second back projection figure corresponding to the second image.Also, in the first back projection figure and the second back projection figure includes
Region corresponding to flying squirrel.
Step S123:The first back projection figure and the second back projection figure are obtained according to the second preset algorithm
Described in the second transformation matrix corresponding to coordinate points in region corresponding to flying squirrel and meet the of second transformation matrix
Three coordinate points.
Then obtained further according to the first back projection figure corresponding to same predetermined position and the second back projection figure white
The coordinate of color border circular areas, RANSAC matching algorithms are recycled to white in the first back projection figure and the second back projection figure
The coordinate of border circular areas is matched, and obtains the point of best match.Specifically matching algorithm thought is:Taken out at random from sample set
Select a RANSAC sample, i.e. 4 matching double points;Transformation matrix M is calculated according to this 4 matching double points;According to sample set, conversion
Matrix M, the consistent collection for meeting current transform matrix is calculated with error metrics function, and return to consistent concentration element number;According to
Current consistent concentration element number judges whether that optimal (maximum) unanimously collects, if the then current optimal unanimously collection of renewal;Renewal is worked as
Preceding error probability p, repeated the above steps if p is more than the minimum error probability allowed and continue iteration, until current erroneous Probability p
Less than minimum error probability.So as to can finally obtain optimal transformation matrix, as the second transformation matrix, and be expired
The Best Point of the second transformation matrix of foot is as the 3rd coordinate points.Taken the photograph it is understood that the 3rd coordinate points can be the first CMOS
Coordinate points in first back projection figure corresponding to the first image shot as head in white portion.
Step S124:The flying squirrel is obtained based on the 3rd coordinate points, second transformation matrix and preset model
In the second abscissa, the second ordinate and the first ordinate of the predeterminated position.
Then, based on the second transformation matrix, back projection figure corresponding to another camera corresponding to the 3rd coordinate points is obtained
In flying squirrel corresponding to point.The coordinate of flying squirrel can be obtained based on preset model again.The schematic diagram of preset model may refer to figure
4, preset model is model corresponding to the position relationship of the image of binocular CMOS camera shooting.Wherein, left camera can be the
One CMOS camera, right camera can be the second CMOS camera, and left view can be the first image, and right view can be second
Image, B are the photocentre of the first CMOS camera and the distance between the photocentre of the second CMOS camera, and point P is flying squirrel, PleftFor
Point of the flying squirrel in the first image, PrightThe point for being flying squirrel in the second image, XleftSat for the horizontal of flying squirrel in the first image
Mark, XrightFor the lateral coordinates of flying squirrel in the second image, Y is longitudinal coordinate, the longitudinal coordinate and second of flying squirrel in the first image
The longitudinal coordinate of flying squirrel is consistent in image, and origin is the O in the first imageL, D is parallax, i.e. Xright-Xleft, f is focal length.Root
According to triangle geometrical relationship:It can obtain:It is thus possible to according to the 3rd coordinate of substitution
Point calculates flying squirrel i.e. point P the second abscissa, the second ordinate and the first ordinate, that is, obtains by the second abscissa, the
The first space coordinates that two ordinates and the first ordinate are formed.
Step S125:Repeat first CMOS camera for obtaining the binocular CMOS camera and the 2nd CMOS takes the photograph
As the flying squirrel that head gathers respectively is the first image and the second image of a predeterminated position the step of, it is based on to described
3rd coordinate points, second transformation matrix and preset model obtain second horizontal stroke of the flying squirrel in the predeterminated position
The step of coordinate, the second ordinate and the first ordinate, obtain second horizontal seat of the flying squirrel in the multiple predeterminated position
The first space coordinates that mark, the second ordinate and the first ordinate are formed.
In each predetermined position, repeat step S121- step S124, then the flying squirrel in each predeterminated position can be obtained
The first space coordinates, so as to obtain flying squirrel multiple predeterminated positions respectively corresponding to multiple first space coordinates.
Step S130:Multiple first plane coordinates and multiple first spaces are obtained based on the first preset algorithm
Multiple first position coordinates corresponding to coordinate.
Flying squirrel is being obtained after the first plane coordinates corresponding to multiple predeterminated positions difference and the first space coordinates, then
The lateral coordinates and longitudinal coordinate of first plane coordinates and the first space coordinates are corrected.
Specifically, stating the first plane coordinates includes the first abscissa and the first ordinate, the first space coordinates bag
Include the second abscissa, the second ordinate and the first ordinate.Fig. 5 is referred to, step S130 can include:
Step S131:The multiple first abscissa and multiple described the are obtained based on preset coordinate correcting algorithm
One ordinate, with multiple second abscissas and the correction function of multiple second ordinates.
Specifically, step S131 can include:Based on default Feature Correspondence Algorithm obtain multiple first abscissas with
And the first set that multiple ordinates are formed is mapped to multiple second abscissas and multiple second ordinates
First transformation matrix of the second set of composition;Obtain threeth collection of the second set by first transformation matrix mapping
Close the difference set with the second set;Local derviation of square asking using least square method to the difference set, obtains deviation
The first coordinate points that first abscissa corresponding to minimum difference point and the first ordinate are formed, and the second abscissa and second
The second coordinate points that ordinate is formed;The first fitting a straight line letter is generated based on first coordinate points and second coordinate points
Number is used as the correction function.Multiple first abscissas and multiple vertical seats are obtained based on default Feature Correspondence Algorithm
The first set that mark is formed is mapped to the second set that multiple second abscissas and multiple second ordinates are formed
The first transformation matrix;Obtain threeth set of the second set by first transformation matrix mapping and the described second collection
The difference set of conjunction;Local derviation of square asking using least square method to the difference set, obtains the minimum difference point pair of deviation
The first coordinate points that the first abscissa answered and the first ordinate are formed, and the of the second abscissa and the second ordinate composition
Two coordinate points;The first fitting a straight line function is generated as the correction based on first coordinate points and second coordinate points
Function.
In embodiments of the present invention, default Feature Correspondence Algorithm can be RANSAC algorithms.Certainly, feature is specifically preset
Matching algorithm is not intended as limiting in embodiments of the present invention.
Step S132:Based on the correction function to it is described to multiple first abscissas, multiple described first vertical sit
Mark, multiple second abscissas and multiple second ordinates are corrected, and obtain the flying squirrel in multiple default positions
Put the 3rd abscissa and the 3rd ordinate at place.
After correction function is obtained, further according to the correction function for the first fitting a straight line function to multiple first abscissas,
Multiple first ordinates, multiple second abscissas and multiple second ordinates are corrected.Specifically, same first space is sat
The second abscissa and the second ordinate in mark may be constructed the second plane coordinates.Then take again straight close to the described first fitting
The point of straight line corresponding to line function, it is hereby achieved that remaining flat after being corrected in the first plane coordinates and the second plane coordinates
Areal coordinate, each the abscissa in remaining plane coordinates and ordinate are sat respectively as the 3rd abscissa and the 3rd are vertical
Mark, that is, flying squirrel is obtained in the 3rd abscissa of multiple predetermined positions and the 3rd ordinate.
Step S133:Erected based on multiple 3rd abscissas, multiple 3rd ordinates and multiple described first
First position coordinate of the flying squirrel described in Coordinate generation in multiple predetermined positions.
Then according to flying squirrel in the 3rd abscissa, the 3rd ordinate and the first ordinate of each predeterminated position, generation
First position coordinate of the flying squirrel in each predetermined position.It is hereby achieved that flying squirrel is in the first position of multiple predetermined positions
Coordinate, and include abscissa, ordinate and ordinate in the coordinate of first position.In addition, abscissa and ordinate are
It is corrected according to the location data that flying squirrel itself gyro data and the image shot based on binocular CMOS camera are obtained
Obtain afterwards, there is reliability higher.
Step S140:The flying squirrel is generated based on the multiple first position coordinate and multiple attitude angle datas to exist
Second place data corresponding to the multiple predeterminated position difference.
After acquisition includes the first position coordinate of abscissa, ordinate and ordinate, then based on flying squirrel itself gyro
The attitude angle data of instrument sensor measure, can obtain flying squirrel in each predetermined position second place data, that is, obtain flying squirrel
Final six-freedom degree α, beta, gamma, x, y, z.It is thus possible under dark condition, the 3 d pose number of flying squirrel is preferably obtained
According to i.e. six-freedom degree.
Second embodiment
Second embodiment of the invention provides a kind of 3 d pose positioner 200, refers to Fig. 6, and the 3 d pose is determined
Position device 200 includes the first data acquisition module 210, the second data acquisition module 220, processing module 230 and data generation
Module 240.Wherein, first data acquisition module 210 is used for the sensing for obtaining the flying squirrel for being internally provided with infrared diode
The flying squirrel of device measure includes in multiple first position data, the first position data corresponding to multiple predeterminated positions difference
Attitude angle data and the first plane coordinates;Second data acquisition module 220 is used for basis and is provided with infrared filter
The flying squirrel of binocular CMOS camera collection obtains the flying squirrel described more in the location drawing picture of the multiple predeterminated position
Multiple first space coordinates corresponding to individual predeterminated position difference;The processing module 230 is used to obtain based on the first preset algorithm
Multiple first position coordinates corresponding to multiple first plane coordinates and multiple first space coordinates;The data life
It is used to generate the flying squirrel described based on the multiple first position coordinate and multiple attitude angle datas into module 240
Second place data corresponding to multiple predeterminated positions difference.
In embodiments of the present invention, first plane coordinates includes the first abscissa and the first ordinate, and described
One space coordinates includes the second abscissa, the second ordinate and the first ordinate.Fig. 7 is referred to, the processing module 230 is wrapped
Include correction function acquiring unit 231, correction unit 232 and execution unit 233.Wherein, the correction function acquiring unit 231
For based on preset coordinate correcting algorithm obtain it is described state the first abscissa and multiple first ordinates, with multiple institutes
State the correction function of the second abscissa and multiple second ordinates;The correction unit 232 is used to be based on the correction
To multiple first abscissas, multiple first ordinates, multiple second abscissas and multiple described in function pair
Second ordinate is corrected, and obtains the flying squirrel in the 3rd abscissa of multiple predetermined positions and the 3rd vertical seat
Mark;The execution unit 233 is used for based on multiple 3rd abscissas, multiple 3rd ordinates and multiple described the
One ordinate generates first position coordinate of the flying squirrel in multiple predetermined positions.
Further, the correction function acquiring unit 231 includes the first correction function acquisition subelement, the second correction letter
Number obtains subelement, the 3rd correction function obtains subelement and the 4th correction function obtains subelement.Wherein, first school
Positive function obtains subelement and is used to obtain multiple first abscissas and multiple described vertical based on default Feature Correspondence Algorithm
The first set that coordinate is formed is mapped to the second collection that multiple second abscissas and multiple second ordinates are formed
The first transformation matrix closed;Second correction function obtains subelement and is used to obtain the second set by the described first change
Change the 3rd set and the difference set of the second set of matrix mapping;3rd correction function obtains subelement and is used for profit
Local derviation of square asking with least square method to the difference set, obtain the first abscissa corresponding to the minimum difference point of deviation with
The first coordinate points that first ordinate is formed, and the second coordinate points that the second abscissa and the second ordinate are formed;Described
Four correction functions obtain subelement and are used to generate the first fitting a straight line based on first coordinate points and second coordinate points
Function is as the correction function.
In embodiments of the present invention, Fig. 8 is referred to, second data acquisition module 220 includes image acquisition unit
221st, graphics processing unit 222, matching treatment unit 223 and coordinate acquiring unit 224.Wherein, described image acquiring unit
221 be used for obtain the binocular CMOS camera the first CMOS camera and the second CMOS camera gather respectively it is described
First image and second image of the flying squirrel in a predeterminated position;Described image processing unit 222 is used to obtain described the
Second back projection figure corresponding to first back projection figure corresponding to one image and second image, described first reversely throws
Shadow figure and the second back projection figure include region corresponding to the flying squirrel;The matching treatment unit 223 is used for root
Area corresponding to flying squirrel described in the first back projection figure and the second back projection figure is obtained according to the second preset algorithm
Second transformation matrix corresponding to coordinate points in domain and the 3rd coordinate points for meeting second transformation matrix;The coordinate obtains
Unit 224 is taken to be used to obtain the flying squirrel in institute based on the 3rd coordinate points, second transformation matrix and preset model
State the second abscissa, the second ordinate and the first ordinate of predeterminated position.
Further, described image acquiring unit 221 includes the first image acquisition subelement, the second image obtains subelement
And the 3rd image obtain subelement.Wherein, described first image obtains subelement and is used to control first CMOS camera
And second CMOS camera obtain the 3rd image and the 4th image of the flying squirrel;Second image obtains subelement and used
In acquisition the 3rd image and the 4th image, corresponding first frame selects image and the second frame to select image respectively, described
First frame select image and second frame to select image be image corresponding to frame favored area corresponding to the flying squirrel;3rd figure
The flying squirrel gathered respectively when first CMOS camera and second CMOS camera as obtaining subelement to be used for
Image and second frame is selected to select images match with first frame respectively in the image of the predeterminated position, then by described
The image of one CMOS camera collection is as the first image, and the image of the second CMOS camera collection is as the second image.
3rd embodiment
Third embodiment of the invention provides a kind of electronic equipment 100, refers to Fig. 1, and the electronic equipment 100 includes storage
Device 102 and processor 106, the memory 102 are couple to the processor 106, the store instruction of memory 102, work as institute
Stating when instruction is performed by the processor 106 makes the processor 106 perform following operation:Acquisition is internally provided with infrared two pole
The flying squirrel of the sensor measure of the flying squirrel of pipe multiple predeterminated positions respectively corresponding to multiple first position data, described the
One position data includes attitude angle data and the first plane coordinates;According to the binocular CMOS camera for being provided with infrared filter
The flying squirrel of collection obtains the flying squirrel in the location drawing picture of the multiple predeterminated position and distinguished in the multiple predeterminated position
Corresponding multiple first space coordinates;Multiple first plane coordinates and multiple described the are obtained based on the first preset algorithm
Multiple first position coordinates corresponding to one space coordinates;Based on the multiple first position coordinate and multiple attitude angle numbers
According to the generation flying squirrel in second place data corresponding to the multiple predeterminated position difference.
In summary, three-dimensional attitude positioning method provided in an embodiment of the present invention, device and electronic equipment, by acquisition
Portion is provided with the flying squirrel of the sensor measure of the flying squirrel of infrared diode multiple first corresponding to multiple predeterminated positions difference
Data are put, first position data include attitude angle data and the first plane coordinates;Then basis is provided with infrared filter
The flying squirrel of binocular CMOS camera collection is right respectively in multiple predeterminated positions in the location drawing picture acquisition flying squirrel of multiple predeterminated positions
Multiple first space coordinates answered;Multiple first plane coordinates are obtained based on the first preset algorithm again and multiple first spaces are sat
Multiple first position coordinates corresponding to mark;It is finally based on multiple first position coordinates and multiple attitude angle datas generation flying squirrel exists
Second place data corresponding to multiple predeterminated positions difference.It is thus possible to three-dimensional appearance corresponding to flying squirrel is obtained under dark condition
State data, to solve the problems, such as that the 3 d pose location data of flying squirrel can not be got under dark condition.
It should be noted that each embodiment in this specification is described by the way of progressive, each embodiment weight
Point explanation is all difference with other embodiment, between each embodiment identical similar part mutually referring to.
For device class embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is joined
See the part explanation of embodiment of the method.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, it can also be passed through
Its mode is realized.Device embodiment described above is only schematical, for example, the flow chart and block diagram in accompanying drawing show
Device, architectural framework in the cards, the work(of method and computer program product of multiple embodiments according to the present invention are shown
Can and it operate.At this point, each square frame in flow chart or block diagram can represent one of a module, program segment or code
Point, a part for the module, program segment or code includes one or more and is used to realize the executable of defined logic function
Instruction.It should also be noted that at some as in the implementation replaced, the function of being marked in square frame can also be with different from attached
The order marked in figure occurs.For example, two continuous square frames can essentially perform substantially in parallel, they also may be used sometimes
To perform in the opposite order, this is depending on involved function.It is it is also noted that each in block diagram and/or flow chart
The combination of square frame and the square frame in block diagram and/or flow chart, can use function or action as defined in performing it is special based on
The system of hardware is realized, or can be realized with the combination of specialized hardware and computer instruction.
In addition, each functional module in each embodiment of the present invention can integrate to form an independent portion
Point or modules individualism, can also two or more modules be integrated to form an independent part.
If the function is realized in the form of software function module and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.Need
Illustrate, herein, such as first and second or the like relational terms be used merely to by an entity or operation with
Another entity or operation make a distinction, and not necessarily require or imply between these entities or operation any this reality be present
The relation or order on border.Moreover, term " comprising ", "comprising" or its any other variant are intended to the bag of nonexcludability
Contain, so that process, method, article or equipment including a series of elements not only include those key elements, but also including
The other element being not expressly set out, or also include for this process, method, article or the intrinsic key element of equipment.
In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including the key element
Process, method, other identical element also be present in article or equipment.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.It should be noted that:Similar label and letter exists
Similar terms is represented in following accompanying drawing, therefore, once being defined in a certain Xiang Yi accompanying drawing, is then not required in subsequent accompanying drawing
It is further defined and explained.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (10)
1. a kind of three-dimensional attitude positioning method, it is characterised in that methods described includes:
The flying squirrel for obtaining the sensor measure for the flying squirrel for being internally provided with infrared diode is right respectively in multiple predeterminated positions
The multiple first position data answered, the first position data include attitude angle data and the first plane coordinates;
The flying squirrel that binocular CMOS camera according to infrared filter is provided with gathers is in the position of the multiple predeterminated position
Put image and obtain the flying squirrel in multiple first space coordinates corresponding to the multiple predeterminated position difference;
Obtained based on the first preset algorithm more corresponding to multiple first plane coordinates and multiple first space coordinates
Individual first position coordinate;
The flying squirrel is generated the multiple default based on the multiple first position coordinate and multiple attitude angle datas
Second place data corresponding to the difference of position.
2. according to the method for claim 1, it is characterised in that first plane coordinates includes the first abscissa and the
One ordinate, first space coordinates includes the second abscissa, the second ordinate and the first ordinate, described to be based on first
Preset algorithm obtains multiple first positions corresponding to multiple first plane coordinates and multiple first space coordinates and sat
Mark, including:
The multiple first abscissa and multiple first ordinates are obtained based on preset coordinate correcting algorithm, it is and more
The correction function of individual second abscissa and multiple second ordinates;
Based on the correction function to described to multiple first abscissas, multiple first ordinates, multiple described
Two abscissas and multiple second ordinates are corrected, and obtain threeth horizontal seat of the flying squirrel in multiple predetermined positions
It is marked with and the 3rd ordinate;
It is described winged based on multiple 3rd abscissas, multiple 3rd ordinates and multiple first ordinate generations
First position coordinate of the mouse in multiple predetermined positions.
3. according to the method for claim 2, it is characterised in that described the multiple based on the acquisition of preset coordinate correcting algorithm
First abscissa and multiple first ordinates, with multiple second abscissas and multiple described second vertical seats
Target correction function, including:
Multiple first abscissas and the first collection of multiple ordinate compositions are obtained based on default Feature Correspondence Algorithm
Close the first transformation matrix for being mapped to the second set that multiple second abscissas and multiple second ordinates are formed;
Obtain threeth set and the difference collection of the second set of the second set by first transformation matrix mapping
Close;
Local derviation of square asking using least square method to the difference set, it is horizontal to obtain corresponding to the minimum difference point of deviation first
The first coordinate points that coordinate and the first ordinate are formed, and the second coordinate points that the second abscissa and the second ordinate are formed;
The first fitting a straight line function is generated as the correction function based on first coordinate points and second coordinate points.
4. according to the method for claim 1, it is characterised in that the binocular CMOS that the basis is provided with infrared filter takes the photograph
As the flying squirrel of head collection obtains the flying squirrel in the multiple predeterminated position in the location drawing picture of the multiple predeterminated position
Multiple first space coordinates corresponding to respectively, including:
Obtain the first CMOS camera of the binocular CMOS camera and the second CMOS camera gathers respectively described flies
First image and second image of the mouse in a predeterminated position;
The second back projection figure corresponding to the first back projection figure corresponding to described first image and second image is obtained,
The first back projection figure and the second back projection figure include region corresponding to the flying squirrel;
Flying squirrel pair described in the first back projection figure and the second back projection figure is obtained according to the second preset algorithm
Second transformation matrix corresponding to coordinate points in the region answered and the 3rd coordinate points for meeting second transformation matrix;
The flying squirrel is obtained in the predeterminated position based on the 3rd coordinate points, second transformation matrix and preset model
The second abscissa, the second ordinate and the first ordinate;
First CMOS camera for obtaining the binocular CMOS camera and the second CMOS camera is repeated to gather respectively
The flying squirrel the first image and the second image of a predeterminated position the step of, be based on the 3rd coordinate to described
Point, second transformation matrix and preset model obtain second abscissa, second vertical of the flying squirrel in the predeterminated position
The step of coordinate and the first ordinate, obtain second abscissa, second vertical seat of the flying squirrel in the multiple predeterminated position
Be marked with and the first ordinate form the first space coordinates.
5. according to the method for claim 4, it is characterised in that the first CMOS for obtaining the binocular CMOS camera
First image and second of the flying squirrel that camera and the second CMOS camera gather respectively in a predeterminated position
Image, including:
First CMOS camera and the second CMOS camera is controlled to obtain the 3rd image and the 4th figure of the flying squirrel
Picture;
Obtaining the 3rd image and the 4th image, corresponding first frame selects image and the second frame to select image respectively, institute
State the first frame select image and second frame to select image be image corresponding to frame favored area corresponding to the flying squirrel;
When the flying squirrel that first CMOS camera and second CMOS camera gather respectively is in the default position
The image put selects image and second frame to select images match with first frame respectively, then by first CMOS camera
The image of collection is as the first image, and the image of the second CMOS camera collection is as the second image.
6. a kind of 3 d pose positioner, it is characterised in that described device includes:First data acquisition module, the second data
Acquisition module, processing module and data generation module, wherein,
First data acquisition module is used for the described of the sensor measure for obtaining the flying squirrel for being internally provided with infrared diode
Flying squirrel multiple predeterminated positions respectively corresponding to multiple first position data, the first position data include attitude angle data with
And first plane coordinates;
Second data acquisition module is used to be flown according to the described of binocular CMOS camera collection for being provided with infrared filter
Mouse the location drawing picture of the multiple predeterminated position obtain the flying squirrel the multiple predeterminated position respectively corresponding to multiple the
One space coordinates;
The processing module is used to obtain multiple first plane coordinates and multiple described first based on the first preset algorithm
Multiple first position coordinates corresponding to space coordinates;
The data generation module is used for based on the multiple first position coordinate and multiple attitude angle data generation institutes
Flying squirrel is stated in second place data corresponding to the multiple predeterminated position difference.
7. device according to claim 6, it is characterised in that first plane coordinates includes the first abscissa and the
One ordinate, first space coordinates include the second abscissa, the second ordinate and the first ordinate, the processing module
Including correction function acquiring unit, correction unit and execution unit, wherein,
The correction function acquiring unit be used for based on preset coordinate correcting algorithm obtain the multiple first abscissa with
And multiple first ordinates, with multiple second abscissas and the correction function of multiple second ordinates;
The correction unit be used for based on the correction function to it is described to multiple first abscissas, it is multiple described first vertical
Coordinate, multiple second abscissas and multiple second ordinates are corrected, and obtain the flying squirrel multiple default
3rd abscissa of opening position and the 3rd ordinate;
The execution unit is used for based on multiple 3rd abscissas, multiple 3rd ordinates and multiple described first
Ordinate generates first position coordinate of the flying squirrel in multiple predetermined positions.
8. device according to claim 7, it is characterised in that the correction function acquiring unit includes the first correction function
Obtain subelement, the second correction function obtains subelement, the 3rd correction function obtains subelement and the 4th correction function obtains
Subelement, wherein,
First correction function obtains subelement and is used to obtain multiple first abscissas based on default Feature Correspondence Algorithm
And the first set that multiple ordinates are formed is mapped to multiple second abscissas and multiple described second vertical seats
Mark the first transformation matrix of the second set formed;
Second correction function obtains subelement and is used to obtain the second set by first transformation matrix mapping
3rd set and the difference set of the second set;
3rd correction function obtains subelement and is used to square seek local derviation to the difference set using least square method, obtains
Obtain the first coordinate points that the first abscissa and the first ordinate corresponding to the minimum difference point of deviation are formed, and the second abscissa
The second coordinate points formed with the second ordinate;
4th correction function obtains subelement and is used for based on first coordinate points and second coordinate points generation the
One fitting a straight line function is as the correction function.
9. device according to claim 6, it is characterised in that second data acquisition module includes image and obtains list
Member, graphics processing unit, matching treatment unit and coordinate acquiring unit, wherein,
Described image acquiring unit is used for the first CMOS camera for obtaining the binocular CMOS camera and the 2nd CMOS takes the photograph
As the flying squirrel that head gathers respectively is in the first image and the second image of a predeterminated position;
Described image processing unit is used to obtain the first back projection figure corresponding to described first image and second image
Corresponding second back projection figure, the first back projection figure and the second back projection figure include the flying squirrel pair
The region answered;
The matching treatment unit is used to obtain the first back projection figure and described second anti-according to the second preset algorithm
Second transformation matrix corresponding to coordinate points into region corresponding to flying squirrel described in perspective view and meet it is described second conversion
3rd coordinate points of matrix;
The coordinate acquiring unit is used to obtain institute based on the 3rd coordinate points, second transformation matrix and preset model
State second abscissa, second ordinate and first ordinate of the flying squirrel in the predeterminated position.
10. a kind of electronic equipment, it is characterised in that the electronic equipment includes memory and processor, the memory coupling
To the processor, the memory store instruction, make the computing device when executed by the processor
Operate below:
The flying squirrel for obtaining the sensor measure for the flying squirrel for being internally provided with infrared diode is right respectively in multiple predeterminated positions
The multiple first position data answered, the first position data include attitude angle data and the first plane coordinates;
The flying squirrel that binocular CMOS camera according to infrared filter is provided with gathers is in the position of the multiple predeterminated position
Put image and obtain the flying squirrel in multiple first space coordinates corresponding to the multiple predeterminated position difference;
Obtained based on the first preset algorithm more corresponding to multiple first plane coordinates and multiple first space coordinates
Individual first position coordinate;
The flying squirrel is generated the multiple default based on the multiple first position coordinate and multiple attitude angle datas
Second place data corresponding to the difference of position.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710961392.1A CN107608541B (en) | 2017-10-17 | 2017-10-17 | Three-dimensional attitude positioning method and device and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710961392.1A CN107608541B (en) | 2017-10-17 | 2017-10-17 | Three-dimensional attitude positioning method and device and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107608541A true CN107608541A (en) | 2018-01-19 |
CN107608541B CN107608541B (en) | 2021-03-05 |
Family
ID=61077410
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710961392.1A Active CN107608541B (en) | 2017-10-17 | 2017-10-17 | Three-dimensional attitude positioning method and device and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107608541B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111031558A (en) * | 2019-12-23 | 2020-04-17 | 安徽理工大学 | Mobile traffic prediction method and device, computer equipment and storage medium |
CN112017238A (en) * | 2019-05-30 | 2020-12-01 | 北京初速度科技有限公司 | Method and device for determining spatial position information of linear object |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103337066A (en) * | 2013-05-27 | 2013-10-02 | 清华大学 | Calibration method for 3D (three-dimensional) acquisition system |
CN104007846A (en) * | 2014-05-22 | 2014-08-27 | 深圳市宇恒互动科技开发有限公司 | Three-dimensional figure generating method and electronic whiteboard system |
CN105222772A (en) * | 2015-09-17 | 2016-01-06 | 泉州装备制造研究所 | A kind of high-precision motion track detection system based on Multi-source Information Fusion |
CN106152937A (en) * | 2015-03-31 | 2016-11-23 | 深圳超多维光电子有限公司 | Space positioning apparatus, system and method |
CN106204605A (en) * | 2016-07-15 | 2016-12-07 | 上海乐相科技有限公司 | A kind of localization method and device |
CN106372552A (en) * | 2016-08-29 | 2017-02-01 | 北京理工大学 | Human body target identification and positioning method |
CN106525003A (en) * | 2016-12-16 | 2017-03-22 | 深圳市未来感知科技有限公司 | Method for measuring attitude on basis of binocular vision |
CN106774880A (en) * | 2010-12-22 | 2017-05-31 | Z空间股份有限公司 | The three-dimensional tracking in space of user control |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101238428B (en) * | 2005-08-22 | 2012-05-30 | 叶勤中 | Free-space pointing and handwriting |
CN107102749B (en) * | 2017-04-23 | 2019-11-08 | 吉林大学 | A kind of three-dimensional pen type localization method based on ultrasonic wave and inertial sensor |
-
2017
- 2017-10-17 CN CN201710961392.1A patent/CN107608541B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106774880A (en) * | 2010-12-22 | 2017-05-31 | Z空间股份有限公司 | The three-dimensional tracking in space of user control |
CN103337066A (en) * | 2013-05-27 | 2013-10-02 | 清华大学 | Calibration method for 3D (three-dimensional) acquisition system |
CN104007846A (en) * | 2014-05-22 | 2014-08-27 | 深圳市宇恒互动科技开发有限公司 | Three-dimensional figure generating method and electronic whiteboard system |
CN106152937A (en) * | 2015-03-31 | 2016-11-23 | 深圳超多维光电子有限公司 | Space positioning apparatus, system and method |
CN105222772A (en) * | 2015-09-17 | 2016-01-06 | 泉州装备制造研究所 | A kind of high-precision motion track detection system based on Multi-source Information Fusion |
CN106204605A (en) * | 2016-07-15 | 2016-12-07 | 上海乐相科技有限公司 | A kind of localization method and device |
CN106372552A (en) * | 2016-08-29 | 2017-02-01 | 北京理工大学 | Human body target identification and positioning method |
CN106525003A (en) * | 2016-12-16 | 2017-03-22 | 深圳市未来感知科技有限公司 | Method for measuring attitude on basis of binocular vision |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112017238A (en) * | 2019-05-30 | 2020-12-01 | 北京初速度科技有限公司 | Method and device for determining spatial position information of linear object |
CN111031558A (en) * | 2019-12-23 | 2020-04-17 | 安徽理工大学 | Mobile traffic prediction method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107608541B (en) | 2021-03-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11232286B2 (en) | Method and apparatus for generating face rotation image | |
CN104781849B (en) | Monocular vision positions the fast initialization with building figure (SLAM) simultaneously | |
CN110363116B (en) | Irregular human face correction method, system and medium based on GLD-GAN | |
CN110222611A (en) | Human skeleton Activity recognition method, system, device based on figure convolutional network | |
WO2020042970A1 (en) | Three-dimensional modeling method and device therefor | |
CN110472612B (en) | Human behavior recognition method and electronic equipment | |
WO2020125499A1 (en) | Operation prompting method and glasses | |
CN110168477A (en) | Deep learning system for cuboid detection | |
US11100669B1 (en) | Multimodal three-dimensional object detection | |
CN108012559A (en) | Automatic threedimensional model generation | |
CN107004275A (en) | For determining that at least one of 3D in absolute space ratio of material object reconstructs the method and system of the space coordinate of part | |
CN108701359A (en) | Across the video frame tracking interest region with corresponding depth map | |
CN109214366A (en) | Localized target recognition methods, apparatus and system again | |
CN110458805A (en) | Plane detection method, computing device and circuit system | |
CN107111880A (en) | Disposal is blocked for computer vision | |
WO2019035155A1 (en) | Image processing system, image processing method, and program | |
WO2018067978A1 (en) | Method and apparatus for generating two-dimensional image data describing a three-dimensional image | |
WO2020215283A1 (en) | Facial recognition method, processing chip and electronic device | |
CN111091075A (en) | Face recognition method and device, electronic equipment and storage medium | |
CN109063776A (en) | Image identifies network training method, device and image recognition methods and device again again | |
CN107122754A (en) | Posture identification method and device | |
CN109948439A (en) | A kind of biopsy method, system and terminal device | |
CN107704106A (en) | Attitude positioning method, device and electronic equipment | |
CN112581540A (en) | Camera calibration method based on human body posture estimation in large scene | |
CN110147708A (en) | A kind of image processing method and relevant apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20221124 Address after: 212310 Workshop 7 #, Dezi Industrial Park, south of Liyao Road, Danyang Development Zone, Zhenjiang City, Jiangsu Province Patentee after: Jiangsu shiruidi photoelectric Co.,Ltd. Patentee after: NINGBO THREDIM OPTOELECTRONICS Co.,Ltd. Address before: 315000 No.58, Jingu Middle Road (West), Yinzhou District, Ningbo City, Zhejiang Province Patentee before: NINGBO THREDIM OPTOELECTRONICS Co.,Ltd. |
|
TR01 | Transfer of patent right |