CN107490346A - A kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model - Google Patents
A kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model Download PDFInfo
- Publication number
- CN107490346A CN107490346A CN201710727530.XA CN201710727530A CN107490346A CN 107490346 A CN107490346 A CN 107490346A CN 201710727530 A CN201710727530 A CN 201710727530A CN 107490346 A CN107490346 A CN 107490346A
- Authority
- CN
- China
- Prior art keywords
- image
- rfid label
- label tag
- rfid
- level 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
For the demand for going out to be put in storage information gathering and goods checking of goods in modern wisdom warehouse logisticses, it is proposed a kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model, the image of RFID label tag is obtained from multi-angle by using two cameras, the image of acquisition is handled using iterative Threshold segmentation and morphological method, using template matching method, the three-dimensional coordinate of RFID label tag is obtained.This method effectively reduces the complexity of algorithm, can obtain the three-dimensional coordinate of RFID label tag in real time.This invention has important theory and application value to modern wisdom warehouse logisticses.
Description
Technical field
The present invention relates to RFID technique and Internet of Things application field, and in particular to RFID multi-tag Network Three-dimensionals coordinate determines
And network modelling, particularly introduce 3D vision analysis method and three-dimensional measurement modeling is carried out to RFID multi-tags network, belong to
Metrology and measurement field.
Background technology
Radio frequency identification (Radio Frequency Identification, RFID) as it is a kind of it is novel it is contactless from
Dynamic identification technology, obtains extensive use, particularly in intelligence in various fields such as modern logistics, intelligent transportation, the production automations
In intelligent logistics, due to consideration that the efficiency of system recognition for batch goods using substantial amounts of RFID label tag, it is necessary to go out storage
Information gathering and goods checking, and the modeling for RFID multi-tag networks at this stage and the identification of RFID multi-tags, distribution,
Permutation and combination, positioning etc. lack a kind of effective automatic measurement and calculate means.
In 3-D view measurement modeling field, three-dimensional measurement modeling is carried out to image using single camera in existing method,
Needing constantly to adjust camera orientation, obtain the subject image under same state from different perspectives, complex operation, real-time is poor,
It is difficult to be applicable the higher occasion of requirement of real-time.Three-dimensional measurement modeling is carried out to image using single camera in existing literature
It is fewer, and it is even more to be rarely reported that three-dimensional measurement modeling is carried out to RFID multi-tags network using the method for image.In order to meet
The demand for going out to be put in storage information gathering and goods checking of goods in modern wisdom warehouse logisticses, found and calculated using image correlation theory
The method that method complexity is low, amount of calculation is small, efficiency high and robustness are good carries out three-dimensional measurement modeling to RFID multi-tags network just
Seem highly significant.Use level, vertical two cameras in the present invention, the image information of RFID label tag, drop are obtained from multi-angle
The low method using image carries out the complexity of three-dimensional measurement modeling to RFID label tag, and method proposed by the present invention has fast
Speed, high accuracy and real-time the advantages of obtaining RFID label tag three-dimensional coordinate.
In specific algorithm, it is related to iterative Threshold segmentation, Morphological scale-space method and template matching algorithm, it is iterative
Threshold segmentation is more effective method in the segmentation of threshold method image, and the optimal threshold of segmentation is obtained by way of iteration,
With certain adaptivity.Morphology Algorithm such as can be corroded and be expanded on the basis of Threshold segmentation at the form to image
Operation is learned, to retain and extract the particular geometric feature in image, and morphological method is easy to be realized with the mode of parallel processing,
Real-time is higher.Template matching algorithm is convenient so that its computational methods is simple, template is chosen, it is easy to accomplish the advantages that, it is especially suitable
In the higher Internet of Things field of requirement of real-time.
The content of the invention
The present invention proposes a kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model, comprises the following steps：
First step：Build test platform step, test platform by RFID reader, reading and writing device antenna, RFID label tag,
RFID label tag support, control computer, servomotor, vertical camera, level camera, guide rail, rotating disk are formed, RFID label tag support
Mark point is posted in bottom, and RFID reader is connected with reading and writing device antenna, and RFID reader is connected with control computer, vertical camera
It is connected respectively with control computer with level camera；
Second step：RFID label tag perpendicular plan view is entered as acquisition step using vertical camera to rotating disk and RFID label tag
Row IMAQ, image is handled using iterative Threshold segmentation and morphological method, and to whole RFID label tags
Point is numbered；
Third step：RFID label tag radial distance extraction step, the rotating disk obtained in above-mentioned second step are vertically overlooked
Two strings are taken on image, make the perpendicular bisector of string, then the intersection point of perpendicular bisector is center of turntable, chooses one of them
RFID label tag point is template, and i-th of RFID label tag point is matched using template matches, obtains i-th of RFID
Distance r of the label mark point to center of turntablei, as i-th of RFID label tag radial distance；
Four steps：RFID label tag horizontal coordinate measuring process, regulation servomotor drive turntable rotation, obtained i-th
The angle, θ of RFID label tag rotationi, then θiWith the r obtained in above-mentioned third stepiThe level of as i-th RFID label tag point
Coordinate parameter, it is (r further to obtain i-th of RFID label tag horizontal coordinateicosθi, risinθi)；
5th step：RFID label tag side elevation image acquisition step, control computer control servomotor drive turntable rotation,
Control computer controlled level camera carries out front and rear adjustment, makes level camera to one of label blur-free imaging, with the label
For template, the vertical range h, i.e. template of measurement module central point to rotating disk vertical coordinate, make level camera to i-th of RFID
Label is accurately focused, and obtains i-th of RFID label tag side elevation image, and template and i-th of RFID label tag are carried out using template matches
Matching, calculate the number of pixels difference c between the central point and template center's point of i-th of RFID label tagi；
6th step：RFID label tag vertical coordinate measuring process, according to Similar Principle of Triangle, determine each picture in image
The size a of the plain length of side, according to the vertical coordinate of side elevation image tag template and i-th RFID label tag with template in vertical direction
Number of pixels mathematic interpolation draw the vertical coordinate H of i-th of RFID label tag in vertical directioni, when i-th RFID label tag
Central spot is in the lower section of template center's point, Hi=h-ci× a, when the central spot of i-th of RFID label tag is in template center's point
Top, Hi=h+ci×a；
7th step：RFID label tag three-dimensional coordinate determines step, and it is (r to determine i-th of RFID label tag three-dimensional coordinateicosθi,
risinθi, Hi)；
8th step：Repeat it is above-mentioned third and fourth, five, six, seven steps, measure all RFID label tags horizontal coordinate and hang down
Straight coordinate, that is, obtain the three-dimensional coordinate of all RFID label tags.
A kind of RFID multi-tags Network Three-dimensional measurement modeling method of above-described view-based access control model, wherein second step institute
Iterative Threshold segmentation is stated, step is as follows：
Step 1：Perpendicular plan view picture is normalized, setting iteration convergence parameter T0, and select one initially
Estimation threshold value T1=(min g (x, y)+max g (x, y))/2, wherein (x, y) is the coordinate of pixel in image, g (x, y)
For the image intensity value after normalization, min g (x, y) are g (x, y) minimum value, and max g (x, y) are g (x, y) maximum；
Step 2：With estimation threshold value T1Split perpendicular plan view picture, perpendicular plan view picture is divided into G1And G2Two parts, its
In, G1So that (x, y) | g (x, y) ＞ T1, G2So that (x, y) | g (x, y) ＜ T1}；
Step 3：Calculate G1And G2The average gray value μ of middle all pixels1And μ2, and new threshold value T2=(μ1+μ2)/
2；
Step 4：If | T2-T2| ＜ T0, then T2As optimal threshold, otherwise, by T2It is assigned to T1；
Step 5：Above step two, three, four is repeated, until obtaining optimal threshold, utilizes the optimal threshold T finally obtained2
Row threshold division is entered to perpendicular plan view picture, obtains the binary image I of perpendicular plan view picture.
A kind of RFID multi-tags Network Three-dimensional measurement modeling method of above-described view-based access control model, wherein second step institute
Morphological method is stated, step is as follows：
Step 1：Expansive working, the image after being expanded are carried out to the binary image of perpendicular plan view pictureWherein B is structural element, and I is the binary image of perpendicular plan view picture,Represent expansion, P1After expansion
Image；
Step 2：Etching operation, the image P after being corroded are carried out to image2=P1Θ B, wherein B are structural element, P1
For the image after expansion, Θ represents corrosion, P2For the image after corrosion；
Step 3：The operation of an above step one and step 2 is repeated, padding then is performed to image again, obtained
To image P3, to P3Step 2 operation is performed, obtains the image after Morphological scale-space.
A kind of above-described view-based access control model RFID multi-tags Network Three-dimensional measurement modeling method, wherein third step and
Template matches described in 5th step, step are as follows：
Step 1：A certain specific image is selected as reference template image, in the region of search of image known to point-by-point translation
Reference template image, each pixel in traversal search region；
Step 2：Determine normalized-cross-correlation function
An equal amount of region of search image in reference template image and original image is matched, wherein, (m, n) sits for pixel
Mark, T (m, n) is reference template image,For reference template image average, M is pixel
The maximum of point coordinates abscissa, N be pixel point coordinates row coordinate maximum, SI, j(m, n) is region of search image,For the average of region of search image；
Step 3：Reference template image is moved into next pixel, repeats above step two, until all positions are all
After matching is completed, regions of the normalized-cross-correlation function NC (i, j) more than given threshold λ is the Matching band to be found
Domain.
The RFID multi-tags Network Three-dimensional measurement modeling method of above-described a kind of view-based access control model, wherein the 5th step institute
State control computer controlled level camera and carry out front and rear adjustment, step is as follows：
Step 1：Level camera initial position is measured to the distance L of center of turntable1；
Step 2：Control computer control servomotor drives turntable rotation so that i-th of RFID label tag and level camera
In plumbness, the distance between i-th of RFID label tag and level camera d are calculatedi=L1-ri；
Step 3：Calculated level camera is accurately focused the object space distances of needs to i-th of RFID label tagIts
In, l ' is distance of the level camera optical center to ccd sensor inside level camera, and f is level camera focal length；
Step 4：Level camera is accurately focused to i-th of RFID label tag needs the distance, delta L that adjustsi=di-liIf Δ Li
More than zero, level camera moves Δ L along close to i-th of RFID label tag directioniIf Δ LiLess than zero, level camera is along away from i-th
Individual RFID label tag direction movement Δ Li。
The RFID multi-tags Network Three-dimensional measurement modeling method of above-described a kind of view-based access control model, wherein the 6th step institute
Similar Principle of Triangle is stated, step is as follows：
Step 1：Control computer controlled level camera carries out front and rear adjustment, makes level camera clear to one of label
Clear imaging, the distance of measurement label to level camera, it is designated as S, level camera optical center to level camera inside ccd sensor
Distance l ', CCD pixel length of side e；
Step 2：Calculate the pixel length of side of image
Brief description of the drawings
Fig. 1：Test platform architecture figure
Fig. 2：7 RFID label tag top views
Fig. 3：1st RFID label tag horizontal coordinate instrumentation plan
Fig. 4：Iterative Threshold segmentation result figure
Fig. 5：Expansion process result figure
Fig. 6：Corrosion treatment result figure
Fig. 7：Fill result figure
Fig. 8：Morphological scale-space result figure
Fig. 9：7 RFID label tag perpendicular plan views are as template matches result figure
Figure 10：1st RFID label tag horizontal image template matches result figure
Embodiment
A kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model, comprises the following steps：
First step：Test platform step is built, test platform is by 1-RFID read write lines, 2- reading and writing device antennas, 3-RFID
Label, 4-RFID label supports, 5- control computers, 6- servomotors, the vertical cameras of 7-, 8- level cameras, 9- guide rails, 10-
Rotating disk is formed, and mark point is posted in 4-RFID label supports bottom, and 1-RFID read write lines control with 2- reading and writing device antennas and 5- respectively
Computer is connected, and the vertical cameras of 7- and 8- level cameras are connected with 5- control computers respectively, and RFID label tag is using hyperfrequency electricity
Subtab-H47, read write line use Impinj Speedway Revolution R420 read write lines, and reading and writing device antenna uses
Laird A9028 far field antennas, maximum RF power outputs are 30dBm, and test platform is as shown in Figure 1；
Second step：RFID label tag perpendicular plan view is entered as acquisition step using vertical camera to rotating disk and RFID label tag
Row IMAQ, perpendicular plan view picture is handled using iterative Threshold segmentation and morphological method, and to all 7
RFID label tag point is numbered, and 7 RFID label tag top views are as shown in Figure 2；
Third step：RFID label tag radial distance extraction step, take on the rotating disk image obtained in above-mentioned second step
Two strings, make the perpendicular bisector of string, then the intersection point of perpendicular bisector is the center of rotating disk, chooses one of RFID label tag
Mark point is template, and the 1st RFID label tag point is matched using template matching algorithm, obtains the 1st RFID label tag
Distance r of the mark point to center of turntable1=198.4mm, as the 1st RFID label tag radial distance；
Four steps：RFID label tag horizontal coordinate measuring process, regulation servomotor drive turntable rotation, obtain the 1st
Angle, θ=48.4 ° of RFID label tag rotation, the then r obtained in θ=48.4 ° and above-mentioned third step1=198.4mm is the 1st
The horizontal coordinate parameter of individual RFID label tag point, the horizontal two-dimension coordinate that the 1st RFID label tag is further calculated are
(131.7mm, 148.4mm), the 1st RFID label tag horizontal coordinate instrumentation plan are as shown in Figure 3；
5th step：RFID label tag side elevation image acquisition step, control computer control servomotor drive turntable rotation,
Control computer controlled level camera carries out front and rear adjustment, makes level camera to one of label blur-free imaging, with the label
For template, the vertical range h=328.0mm, i.e. template of measurement module central point to rotating disk vertical coordinate, make level camera pair
1st RFID label tag is accurately focused, and the 1st RFID label tag side elevation image is obtained, using template matches to template and the 1st RFID
Label is matched, and calculates the number of pixels difference c between the central point and template center's point of the 1st RFID label tag1=71；
6th step：RFID label tag vertical coordinate measuring process, according to Similar Principle of Triangle, determine each picture in image
The size of element is a=0.75mm, wherein, 0.75mm is the size of each pixel length of side, according to the vertical coordinate of template and the 1st
RFID label tag and the number of pixels difference of template in vertical direction, and the 1st RFID label tag central point Y value are big
In template center's point Y value, judgement draws the 1st RFID label tag central point heart point top in a template, so as to calculate
Go out the vertical coordinate H of the 1st RFID label tag in vertical direction1=h+c1× a=327.85+0.75 × 71=381.1mm；
7th step：RFID label tag three-dimensional coordinate determines step, determine the 1st RFID label tag three-dimensional coordinate for (131.7,
148.4 381.1)；
8th step：Repeat it is above-mentioned third and fourth, five, six, seven steps, the horizontal two-dimension for measuring all 7 RFID label tags sits
Mark and vertical coordinate, that is, the three-dimensional coordinate for obtaining all 7 RFID label tags are (131.7,148.4,381.1), (116.5,
179.2,355.9), (- 232.4,200.3,350.5), (- 168.7, -58.8,350.3), (47.5, -106.4,328.5),
(174.2,40.7,340.1), (174.9, -16.7,379.9).
Described in a kind of RFID multi-tags Network Three-dimensional measurement modeling method second step of above-described view-based access control model repeatedly
It is as follows for formula Threshold segmentation, step：
Step 1：Perpendicular plan view picture is normalized, setting iteration convergence parameter T0=0.01, and select one
Individual initial estimation threshold value T1=0.5178；
Step 2：With estimation threshold value T1=0.5178 segmentation perpendicular plan view picture, is divided into G by perpendicular plan view picture1And G2Two
Part, wherein, G1So that (x, y) | g (x, y) ＞ T1, G2So that (x, y) | g (x, y) ＜ T1}；
Step 3：Calculate G1And G2The average gray value μ of middle all pixels1=0.6615 and μ2=0.1165, and new
Threshold value T2=(0.6615+0.1165)/2=0.3890；
Step 4：|T2-T1| ＜ 0.01, then T2As optimal threshold, otherwise, by T2It is assigned to T1；
Step 5：Above step two, three, four is repeated, until obtaining optimal threshold, utilizes the optimal threshold T finally obtained2
Row threshold division is entered to perpendicular plan view picture, obtains the binary image I of perpendicular plan view picture, the binaryzation of perpendicular plan view picture
Image is as shown in Figure 4.
Shape described in a kind of RFID multi-tags Network Three-dimensional measurement modeling method second step of above-described view-based access control model
State method, step are as follows：
Step 1：Expansive working, the image after being expanded are carried out to the binary image of perpendicular plan view pictureWherein B is structural element, and I is the binary image of perpendicular plan view picture,Represent expansion, P1After expansion
Image, the image after expansion are as shown in Figure 5；
Step 2：Etching operation, the image P after being corroded are carried out to image2=P1Θ B, wherein B are structural element, P1
For the image after expansion, Θ represents corrosion, P2For the image after corrosion, the image after corrosion is as shown in Figure 6；
Step 3：The operation of an above step one and step 2 is repeated, padding then is performed to image again, obtained
To image P3, the image after filling is as shown in fig. 7, to P3Step 2 operation is performed, obtains the image after Morphological scale-space, form
It is as shown in Figure 8 to learn processing final effect figure.
A kind of RFID multi-tags Network Three-dimensional measurement modeling method third step and the 5th of above-described view-based access control model
Template matches described in step, step are as follows：
Step 1：A certain specific image is selected as reference template image, in the region of search of image known to point-by-point translation
Reference template image, each pixel in traversal search region；
Step 2：Determine normalized-cross-correlation function
An equal amount of region of search image in reference template image and original image is matched, wherein, (m, n) sits for pixel
Mark, T (m, n) is reference template image,For reference template image average, M is pixel
The maximum of coordinate abscissa, N be pixel point coordinates row coordinate maximum, SI, j(m, n) is region of search image,For the average of region of search image；
Step 3：Reference template image is moved into next pixel, repeats above step two, until all positions are all
After matching is completed, the region that normalized-cross-correlation function NC (i, j) is more than given threshold λ=0.75 is to be found
With region, 7 RFID label tag perpendicular plan views are as template matching results figure as shown in figure 9, the 1st RFID label tag horizontal image mould
Plate matching result figure is as shown in Figure 10.
Control described in a kind of RFID multi-tags Network Three-dimensional measurement step of modeling method the 5th of above-described view-based access control model
Computer controlled level camera processed carries out front and rear adjustment, and step is as follows：
Step 1：Level camera initial position is measured to the distance L of center of turntable1=1.512m；
Step 2：Control computer control servomotor drives turntable rotation so that the 1st RFID label tag and level camera
In plumbness, the distance between the 1st RFID label tag and level camera d are calculated1=1.512m-0.406m=1.106m；
Step 3：Calculated level camera is accurately focused the object space distances of needs to the 1st RFID label tagWherein, l ' is that level camera optical center passes to CCD inside level camera
The distance of sensor, l '=0.00597m, f=0.006m；
Step 4：Level camera is accurately focused to the 1st RFID label tag needs the distance, delta L that adjusts1=d1-|l1|=
1.106m- (1.194m)=- 0.088m, Δ L1Less than zero, level camera moves along away from the 1st RFID label tag direction
0.088m。
Three described in a kind of RFID multi-tags Network Three-dimensional measurement step of modeling method the 6th of above-described view-based access control model
The angular principle of similitude, step are as follows：
Step 1：Control computer controlled level camera carries out front and rear adjustment, makes level camera clear to one of label
Clear imaging, the distance of measurement label to level camera, is designated as S=1.194m, inside level camera optical center to level camera
Distance l '=0.00597m of ccd sensor, e=3.75 μm of the length of side of CCD pixels；
Step 2：Calculate the pixel length of side of image
Claims (6)
1. a kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model, comprises the following steps：
First step：Test platform step is built, test platform is marked by RFID reader, reading and writing device antenna, RFID label tag, RFID
Sign support, control computer, servomotor, vertical camera, level camera, guide rail, rotating disk to form, RFID label tag frame bottom patch
There is mark point, RFID reader is connected with reading and writing device antenna, and RFID reader is connected with control computer, vertical camera and level
Camera is connected with control computer respectively；
Second step：RFID label tag perpendicular plan view carries out figure using vertical camera as acquisition step to rotating disk and RFID label tag
As collection, image is handled using iterative Threshold segmentation and morphological method, and whole RFID label tags are clicked through
Line number；
Third step：RFID label tag radial distance extraction step, the rotating disk perpendicular plan view picture obtained in above-mentioned second step
On take two strings, make the perpendicular bisector of string, then the intersection point of perpendicular bisector is center of turntable, chooses one of RFID mark
Label mark point is template, and i-th of RFID label tag point is matched using template matches, obtains i-th of RFID label tag mark
Distance r of the note point to center of turntablei, as i-th of RFID label tag radial distance；
Four steps：RFID label tag horizontal coordinate measuring process, regulation servomotor drive turntable rotation, obtain i-th of RFID
The angle, θ of label rotationi, then θiWith the r obtained in above-mentioned third stepiThe horizontal coordinate of as i-th RFID label tag point
Parameter, it is (r further to obtain i-th of RFID label tag horizontal coordinateicosθi, risinθi)；
5th step：RFID label tag side elevation image acquisition step, control computer control servomotor drive turntable rotation, control
Computer controlled level camera carries out front and rear adjustment, makes level camera to one of label blur-free imaging, using the label as mould
Plate, the vertical range h, i.e. template of measurement module central point to rotating disk vertical coordinate, make level camera to i-th of RFID label tag
Accurate focusing, is obtained i-th of RFID label tag side elevation image, template and i-th of RFID label tag is matched using template matches,
Calculate the number of pixels difference c between the central point and template center's point of i-th of RFID label tagi；
6th step：RFID label tag vertical coordinate measuring process, according to Similar Principle of Triangle, determine each pixel side in image
Long size a, according to the vertical coordinate of side elevation image tag template and i-th of RFID label tag and the picture of template in vertical direction
Plain number difference, the vertical coordinate H of i-th of RFID label tag in vertical direction is calculatedi, when in i-th of RFID label tag
Heart point is in the lower section of template center's point, Hi=h-ci× a, when the central spot of i-th of RFID label tag is in the upper of template center's point
Side, Hi=h+ci×a；
7th step：RFID label tag three-dimensional coordinate determines step, and it is (r to determine i-th of RFID label tag three-dimensional coordinateicosθi,
risinθi, Hi)；
8th step：Repeat it is above-mentioned third and fourth, five, six, seven steps, measure the horizontal coordinate of all RFID label tags and vertical sit
Mark, that is, obtain the three-dimensional coordinate of all RFID label tags.
2. a kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model according to claim 1, wherein the
Iterative Threshold segmentation, step are as follows described in two steps：
Step 1：Perpendicular plan view picture is normalized, setting iteration convergence parameter T0, and select one initial to estimate
Count threshold value T1=(min g (x, y)+max g (x, y))/2, wherein (x, y) is the coordinate of pixel in image, g (x, y) is to return
Image intensity value after one change, min g (x, y) are g (x, y) minimum value, and max g (x, y) are g (x, y) maximum；
Step 2：With estimation threshold value T1Split perpendicular plan view picture, perpendicular plan view picture is divided into G1And G2Two parts, wherein, G1
So that (x, y) | g (x, y) ＞ T1, G2So that (x, y) | g (x, y) ＜ T1}；
Step 3：Calculate G1And G2The average gray value μ of middle all pixels1And μ2, and new threshold value T2=(μ1+μ2)/2；
Step 4：If | T2-T1| ＜ T0, then T2As optimal threshold, otherwise, by T2It is assigned to T1；
Step 5：Above step two, three, four is repeated, until obtaining optimal threshold, utilizes the optimal threshold T finally obtained2To hanging down
Straight overhead view image enters row threshold division, obtains the binary image I of perpendicular plan view picture.
3. a kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model according to claim 1, wherein the
Morphological method described in two steps, step are as follows：
Step 1：Expansive working, the image after being expanded are carried out to the binary image of perpendicular plan view pictureIts
Middle B is structural element, and I is the binary image of perpendicular plan view picture,Represent expansion, P1For the image after expansion；
Step 2：Etching operation, the image P after being corroded are carried out to image2=P1Θ B, wherein B are structural element, P1To be swollen
Image after swollen, Θ represent corrosion, P2For the image after corrosion；
Step 3：The operation of an above step one and step 2 is repeated, padding then is performed to image again, obtains figure
As P3, to P3Step 2 operation is performed, obtains the image after Morphological scale-space.
4. a kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model according to claim 1, wherein the
Template matches described in three steps and the 5th step, step are as follows：
Step 1：A certain specific image is selected as reference template image, point-by-point translation is known in the region of search of image joins
Examine template image, each pixel in traversal search region；
Step 2：Determine normalized-cross-correlation function
An equal amount of region of search image in reference template image and original image is matched, wherein, (m, n) sits for pixel
Mark, T (m, n) is reference template image,For reference template image average, M is pixel
The maximum of coordinate abscissa, N be pixel point coordinates row coordinate maximum, SI, j(m, n) is region of search image,For the average of region of search image；
Step 3：Reference template image is moved into next pixel, repeats above step two, until all positions all match
After completion, regions of the normalized-cross-correlation function NC (i, j) more than given threshold λ is the matching area to be found.
5. a kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model according to claim 1, wherein the
Control computer controlled level camera described in five steps carries out front and rear adjustment, and step is as follows：
Step 1：Level camera initial position is measured to the distance L of center of turntable1；
Step 2：Control computer control servomotor drives turntable rotation so that i-th of RFID label tag is in level camera
Plumbness, calculate the distance between i-th of RFID label tag and level camera di=L1-ri；
Step 3：Calculated level camera is accurately focused the object space distances of needs to i-th of RFID label tagWherein, l ' is
To the distance of ccd sensor inside level camera, f is level camera focal length for level camera optical center；
Step 4：Level camera is accurately focused to i-th of RFID label tag needs the distance, delta L that adjustsi=di-liIf Δ LiIt is more than
Zero, level camera moves Δ L along close to i-th of RFID label tag directioniIf Δ LiLess than zero, level camera is along away from i-th
RFID label tag direction movement Δ Li。
6. a kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model according to claim 1, wherein the
Similar Principle of Triangle described in six steps, step are as follows：
Step 1：Control computer controlled level camera carry out it is front and rear adjust, make level camera to one of label clearly into
Picture, measurement label arrive the distance of level camera, are designated as S, level camera optical center to level camera inside ccd sensor away from
From l ', the length of side e of CCD pixels；
Step 2：Calculate the pixel length of side of image
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710727530.XA CN107490346B (en) | 2017-08-17 | 2017-08-17 | RFID multi-label network three-dimensional measurement modeling method based on vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710727530.XA CN107490346B (en) | 2017-08-17 | 2017-08-17 | RFID multi-label network three-dimensional measurement modeling method based on vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107490346A true CN107490346A (en) | 2017-12-19 |
| CN107490346B CN107490346B (en) | 2021-05-28 |
Family
ID=60645492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710727530.XA Active CN107490346B (en) | 2017-08-17 | 2017-08-17 | RFID multi-label network three-dimensional measurement modeling method based on vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107490346B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108426527A (en) * | 2018-01-23 | 2018-08-21 | 淮阴工学院 | A kind of RFID tag three-dimensional coordinate automatic testing method based on DLT |
| CN109003261A (en) * | 2018-06-29 | 2018-12-14 | 北京科技大学 | Heterogeneous phase three-dimensional construction method and device |
| CN109061616A (en) * | 2018-08-31 | 2018-12-21 | 南通大学 | A kind of Moving objects location method |
| CN111561869A (en) * | 2020-05-22 | 2020-08-21 | 延锋彼欧武汉汽车外饰系统有限公司 | Intelligent detection device and method for vehicle body space position and application thereof |
| CN111780689A (en) * | 2020-07-13 | 2020-10-16 | 四川大学 | Optimal rotation angle determination method based on cross-correlation structured light 360-degree measurement |
| CN113139395A (en) * | 2021-03-29 | 2021-07-20 | 南京航空航天大学 | Multi-label optimal distribution method of radio frequency identification system based on computer vision |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100866459B1 (en) * | 2007-07-20 | 2008-10-31 | 재단법인서울대학교산학협력재단 | Location tracking system |
| CN101325694A (en) * | 2007-06-13 | 2008-12-17 | 中国科学院自动化研究所 | System and method for monitoring intelligent video combining wireless radio frequency recognition technique |
| CN102184436A (en) * | 2011-05-16 | 2011-09-14 | 重庆大学 | Method for sensing position of object in Internet of things |
| CN102656422A (en) * | 2010-01-20 | 2012-09-05 | 法罗技术股份有限公司 | Multi-functional coordinate measurement machines |
| JP2012221481A (en) * | 2011-04-07 | 2012-11-12 | Lsi Japan Kk | Walking support device for vision-impaired person |
| US8847761B1 (en) * | 2004-10-01 | 2014-09-30 | Emc Corporation | Anonymous transaction tokens |
| US8947678B2 (en) * | 2013-12-11 | 2015-02-03 | Faro Technologies, Inc. | Method for correcting three-dimensional measurements of a spherically mounted retroreflector |
| CN105182319A (en) * | 2015-08-12 | 2015-12-23 | 西安斯凯智能科技有限公司 | Target positioning system and target positioning method based on radio frequency and binocular vision |
| CN105354521A (en) * | 2015-11-27 | 2016-02-24 | 江苏省标准化研究院 | BP neural network-based RFID label distribution optimum configuration method |
| CN105718929A (en) * | 2016-01-21 | 2016-06-29 | 成都信息工程大学 | All-weather unknown environment high precision rapid circular object positioning method and system |
| CN106295936A (en) * | 2015-05-29 | 2017-01-04 | 深圳镭博万科技有限公司 | Wheel hub type identification device and wheel hub mark system for tracing and managing |
| CN106557906A (en) * | 2016-11-30 | 2017-04-05 | 长威信息科技发展股份有限公司 | A kind of warehouse management method and system based on three-dimensional modeling |
| CN108426527A (en) * | 2018-01-23 | 2018-08-21 | 淮阴工学院 | A kind of RFID tag three-dimensional coordinate automatic testing method based on DLT |
-
2017
- 2017-08-17 CN CN201710727530.XA patent/CN107490346B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8847761B1 (en) * | 2004-10-01 | 2014-09-30 | Emc Corporation | Anonymous transaction tokens |
| CN101325694A (en) * | 2007-06-13 | 2008-12-17 | 中国科学院自动化研究所 | System and method for monitoring intelligent video combining wireless radio frequency recognition technique |
| KR100866459B1 (en) * | 2007-07-20 | 2008-10-31 | 재단법인서울대학교산학협력재단 | Location tracking system |
| CN102656422A (en) * | 2010-01-20 | 2012-09-05 | 法罗技术股份有限公司 | Multi-functional coordinate measurement machines |
| JP2012221481A (en) * | 2011-04-07 | 2012-11-12 | Lsi Japan Kk | Walking support device for vision-impaired person |
| CN102184436A (en) * | 2011-05-16 | 2011-09-14 | 重庆大学 | Method for sensing position of object in Internet of things |
| US8947678B2 (en) * | 2013-12-11 | 2015-02-03 | Faro Technologies, Inc. | Method for correcting three-dimensional measurements of a spherically mounted retroreflector |
| CN106295936A (en) * | 2015-05-29 | 2017-01-04 | 深圳镭博万科技有限公司 | Wheel hub type identification device and wheel hub mark system for tracing and managing |
| CN105182319A (en) * | 2015-08-12 | 2015-12-23 | 西安斯凯智能科技有限公司 | Target positioning system and target positioning method based on radio frequency and binocular vision |
| CN105354521A (en) * | 2015-11-27 | 2016-02-24 | 江苏省标准化研究院 | BP neural network-based RFID label distribution optimum configuration method |
| CN105718929A (en) * | 2016-01-21 | 2016-06-29 | 成都信息工程大学 | All-weather unknown environment high precision rapid circular object positioning method and system |
| CN106557906A (en) * | 2016-11-30 | 2017-04-05 | 长威信息科技发展股份有限公司 | A kind of warehouse management method and system based on three-dimensional modeling |
| CN108426527A (en) * | 2018-01-23 | 2018-08-21 | 淮阴工学院 | A kind of RFID tag three-dimensional coordinate automatic testing method based on DLT |
Non-Patent Citations (6)
| Title |
|---|
| M. A. HANNAN: "Radio Frequency Identification (RFID) and communication technologies for solid waste bin and truck monitoring system", 《WASTE MANAGEMENT》 * |
| XIAO ZHUANG: "A novel 3D position measurement and structure prediction method for RFID tag group based on deep belief network", 《MEASUREMENT》 * |
| XIAO ZHUANG: "A novel method for 3D measurement of RFID multi-tag network based on matching vision and wavelet", 《MEASUREMENT SCIENCE AND TECHNOLOGY》 * |
| YUJUN ZHOU: "Optimization Analysis of Distribution of RFID Multitag based on GA-BP Neural Network", 《PROCEEDINGS OF 2017 IEEE 2ND ADVANCED INFORMATION TECHNOLOGY,ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (IAEAC 2017)》 * |
| 俞晓磊: "利用Fisher矩阵的RFID多标签最优分布检测方法", 《西安电子科技大学学报（自然科学版）》 * |
| 刘辉: "RFID标签封装设备中机器视觉系统设计与实现", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108426527A (en) * | 2018-01-23 | 2018-08-21 | 淮阴工学院 | A kind of RFID tag three-dimensional coordinate automatic testing method based on DLT |
| CN109003261A (en) * | 2018-06-29 | 2018-12-14 | 北京科技大学 | Heterogeneous phase three-dimensional construction method and device |
| CN109061616A (en) * | 2018-08-31 | 2018-12-21 | 南通大学 | A kind of Moving objects location method |
| CN109061616B (en) * | 2018-08-31 | 2022-11-04 | 南通大学 | Moving target positioning method |
| CN111561869A (en) * | 2020-05-22 | 2020-08-21 | 延锋彼欧武汉汽车外饰系统有限公司 | Intelligent detection device and method for vehicle body space position and application thereof |
| CN111780689A (en) * | 2020-07-13 | 2020-10-16 | 四川大学 | Optimal rotation angle determination method based on cross-correlation structured light 360-degree measurement |
| CN111780689B (en) * | 2020-07-13 | 2021-06-29 | 四川大学 | Optimal rotation angle determination method based on cross-correlation structured light 360-degree measurement |
| CN113139395A (en) * | 2021-03-29 | 2021-07-20 | 南京航空航天大学 | Multi-label optimal distribution method of radio frequency identification system based on computer vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107490346B (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107490346A (en) | A kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model | |
| CN105740899B (en) | A kind of detection of machine vision image characteristic point and match compound optimization method | |
| CN108597009B (en) | Method for detecting three-dimensional target based on direction angle information | |
| CN106023211B (en) | Robot graphics' localization method and system based on deep learning | |
| CN111768447B (en) | Monocular camera object pose estimation method and system based on template matching | |
| CN101839692A (en) | Method for measuring three-dimensional position and stance of object with single camera | |
| CN108107444A (en) | Substation's method for recognizing impurities based on laser data | |
| CN111553409A (en) | Point cloud identification method based on voxel shape descriptor | |
| CN110084243A (en) | It is a kind of based on the archives of two dimensional code and monocular camera identification and localization method | |
| CN110992422B (en) | Medicine box posture estimation method based on 3D vision | |
| CN112734844A (en) | Monocular 6D pose estimation method based on octahedron | |
| Yang et al. | A method for wafer defect detection using spatial feature points guided affine iterative closest point algorithm | |
| CN115100292A (en) | External parameter online calibration method between laser radar and camera in road environment | |
| CN114241469A (en) | Information identification method and device for electricity meter rotation process | |
| CN109859243A (en) | A kind of motion target tracking method based on dimension self-adaption block particle | |
| CN111167731B (en) | Product sorting method, product sorting system and intelligent sorting robot | |
| Gao et al. | Improved binocular localization of kiwifruit in orchard based on fruit and calyx detection using YOLOv5x for robotic picking | |
| CN114689038B (en) | Fruit detection positioning and orchard map construction method based on machine vision | |
| CN109598261B (en) | Three-dimensional face recognition method based on region segmentation | |
| Zhang et al. | Lidar odometry and mapping based on two-stage feature extraction | |
| CN109635692B (en) | Scene re-identification method based on ultrasonic sensor | |
| Li et al. | Online workpieces recognition for the robotic spray-painting production line with a low-cost RGB-D camera | |
| CN113884025B (en) | Method and device for detecting optical loop of additive manufacturing structure, electronic equipment and storage medium | |
| CN113096104B (en) | Training method and device of target segmentation model and target segmentation method and device | |
| Sheng et al. | Image segmentation and object measurement based on stereo vision |
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 |