CN109029779A - A kind of real-time body's temperature rapid detection method - Google Patents
A kind of real-time body's temperature rapid detection method Download PDFInfo
- Publication number
- CN109029779A CN109029779A CN201810399016.2A CN201810399016A CN109029779A CN 109029779 A CN109029779 A CN 109029779A CN 201810399016 A CN201810399016 A CN 201810399016A CN 109029779 A CN109029779 A CN 109029779A
- Authority
- CN
- China
- Prior art keywords
- value
- line segment
- profile
- angle
- mobile object
- 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
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
- G01K13/20—Clinical contact thermometers for use with humans or animals
Abstract
The present invention relates to a kind of real-time body's temperature rapid detection methods.First, after the simplification profile for obtaining the object of visible light and infrared image, it is compared with the intersection that Dynamic Programming carries out profile, then infrared ray object coincides to similarly spending on highest visible light object through perspective projection conversion, pedestrian's temperature of going forward side by side calculates.The invention enables infrared rays and visible image to merge, in addition to that can obtain body temperature, moreover it is possible to recognize item, can promote identification efficiency, realize human body temperature rapid detection.
Description
Technical field
The present invention relates to a kind of real-time body's temperature rapid detection methods.
Background technique
It is existing based on infrared human body temperature detection mode, due to infrared camera pick-up image and visible image
When differing widely, therefore monitoring temperature through infrored equipment in the past, visible image must be captured through another video camera, then
Artificial comparison identification is carried out, occasion so big in flow of the people realizes human temperature while can not fast implementing human bioequivalence
Degree detection, for this reason, it may be necessary to a kind of automatic ratio for being able to carry out visible image contour of object Yu the hot body profile of infrared image
To, position and coincide, save the troublesome mode manually compared.
The existing pertinent literature merged for visible image with thermal imagery has:
1. dynamic adjusts the strong human face recognition of multiple visible images Yu thermal imagery integration percentage, only honor Master's thesis is applied
Merging for visible light and red heat image is done using discrete wavelet (Discrete Wavelet Transform, DWT),
And with the difference of visible image illuminance, the integration percentage of visible light and thermal imagery is adjusted, then everyone is continuously melted
Group photo is as carrying out linear discriminant formula (Linear Discriminant Analysis, LDA), then by the spy of fused image
Sign parameter is converted, and finally carries out human face recognition using Euclidean distance.
2. the research of infrared ray and visible image fusion under changeability visual environment, Chen Mengyi, generation Red brick picture and text pass
It broadcasts and numerical digit Publishing Master's thesis
It will be red using principal component analysis (Principle Components Analysis, PCA) insertion more analytic sheafs of small echo
Outside line is merged with visible image.Infrared ray is merged with visible image using PCA and DWT respectively first, two kinds of analysis is melted
The advantages of group photo picture, two image of taking-up, simultaneously merges it, obtains the more analytic sheaf fusion evaluations of built-in PC A small echo.It can be different
Possess preferable fusion results under visual environment.
3.Fast and Accurate Registration of Visible and Infrared Videos,
Socheat Sonn, Guillaume-Alexandre Bilodeau,Philippe Galinier,IEEE Conference
on Computer Vision and Pattern Recognition Workshops,pp.308-313,2013
Utilize the orientation problem of the infrared ray and visible light three-dimensional object solved in scene based on key point and temporal information.
It first takes out the profile of object and switchs to polygon, with the vertex of this polygon as key point, to compare.Further according to comparison
Key point calculates transition matrix and is placed in time buffer area, the transition matrix in accumulation buffer, will using this transition matrix
Infrared image is converted and is navigated on visible image.
4.Automatic Image Registration in Infrared-Visible Videos using
Polygon Vertices,Tanushri Chakravorty,Guillaume-Alexandre Bilodeau,Eric
Granger,2014
Object is taken out using background subtracting method, recycles polygonal segments to obtain the shape of target object, then detects shape
Key point on shape, and object is compared according to the convex closure parameter of Euclidean distance and its shape between these key points.It obtains
After comparing key point, key point will be compared and be stored in time buffer area, it is respective to calculate all comparison key points in buffer area
Transition matrix is converted infrared ray using transition matrix, calculates the overlapping ratio of infrared ray and visible image, if than current
Transition matrix it is more preferable, just update transition matrix.
Above-mentioned existing literature is when comparing characteristic point, the line that is linked into Visible Light Characteristics point and infra-red signature point two o'clock
Section angle and length finally calculate the homography matrix for being suitable for whole picture as comparison condition according to the point compared
Infrared ray is converted with this matrix and is merged with visible image by Homography matrix；However, those literature processings can
When the light-exposed automatic positioning with infrared image is with coinciding, it can not achieve the more than one human body of automatic comparison, infrared ray determined
Human body temperature detection is realized in position to position correct on visible image while can not fast implementing human bioequivalence.
Summary of the invention
The purpose of the present invention is to provide a kind of real-time body's temperature rapid detection methods, so that infrared ray and visible image
Fusion, in addition to body temperature can be obtained, moreover it is possible to recognize item, identification efficiency can be promoted, realize human body temperature rapid detection.
To achieve the above object, the technical scheme is that a kind of real-time body's temperature rapid detection method, firstly, taking
After the simplification profile for obtaining the object of visible light and infrared image, compared with the intersection that Dynamic Programming carries out profile, then penetrate
Perspective projection conversion coincides infrared ray object to similarly spending on highest visible light object, pedestrian's thermometer body of going forward side by side
It calculates.
In an embodiment of the present invention, the specific implementation steps are as follows for this method:
Step S1, image is absorbed by infrared camera and visible light photography machine, obtains infrared image and visible light
Image；Then back-packing is gone to obtain mobile object profile using Gauss visible image；By the color space of infrared image from
RGB goes to HSV, obtains mobile object profile according to formula (1)
Wherein, F (x, y) is prospect image, and H (x, y) is form and aspect channel, and x, y are image coordinate；
Step S2, infrared image is obtained with after the profile of each mobile object in visible image, is forced using polygon
Nearly method approaches profile, then and the parameter of each line segment in profile is calculated according to simplification profile, comprising: the angle of line segment
Degree A, the length L of line segment, previous line segment angle rotate the angle of rotation angle PR to the angle of current line segment, current line segment
It rotates to the rotation angle NR of the angle of latter line segment, line segment two-end-point is defined as a and b, then a parameter calculation formula such as (2)
Shown in~(5):
PR=| Current Segment Angle-Previous Segment Angle | (4)
NR=| NextSegment Angle-Current Segment Angle | (5)
Wherein, a, b are the two-end-point for forming line segment, and x, y are image coordinate；
Then profile is compared using Dynamic Programming DP, establishes the data form Datatable of a two-dimensional array, table is big
Small is visible light mobile object line segment quantity × infrared ray mobile object line segment quantity, and the value in table is respectively that visible light moves
The corresponding line segment of animal body profile compared with the corresponding line segment of infrared ray mobile object profile after difference value, compare formula
Such as (6)
Wherein, formula (6) indicates that current computing object is the value on xth column, the column y in Datatable, that is, compares visible light
The length L, previous of y-th of line segment of mobile object R and the angle A of line segment on the xth line segment of infrared ray mobile object T, line segment
The angle of line segment is rotated to the angle of the rotation angle PR of the angle of current line segment, current line segment and is rotated to the angle of latter line segment
The value of rotation angle NR this four differences, W1, W2, W3 and W4 are corresponding weight；
Then according to data form, using Dynamic Programming DP with mobile object profile is two-by-two the total poor of one group of calculating profile
Different value；
Step S3: being that each mobile object profile calculates a homography matrix according to comparison result, by the movement of infrared ray
After object individually takes out, infrared ray mobile object is converted into visible light mobile object using perspective conversion, finally by infrared ray
Mobile object is fused on visible light mobile object, and pedestrian's temperature of going forward side by side calculates.
In an embodiment of the present invention, in step S2, use Dynamic Programming DP by mobile object profile two-by-two be one group in terms of
The specific implementation steps are as follows for the total variances value of calculation profile:
Step S21: DP table DPtable is initialized according to following four conditional definitions, wherein DPtable (x, y) is indicated
The value of DPtable xth column, the column y, it is seen that light mobile object R line segment quantity is n, infrared ray mobile object T line segment quantity is
M, and with A, B, C respectively represent three Fang Xiang ↖, ←, ↑, X then represent without tracking:
(1) if x=0, y=0, then the value of DPtable (0,0) be equal to Datatable (0,0) value, Pathtable (0,
0) value is X；
(2) if x=0, y ≠ 0, then the value of DPtable (0, y) is equal to DPtable (0, y-1)+Datatable's (0, y)
Value, the value of Pathtable (0, y) are C；
(3) if x ≠ 0, y=0, then the value of DPtable (x, 0) is equal to DPtable (x-1,0)+Datatable's (x, 0)
Value, the value of Pathtable (x, 0) are B；
(4) if x ≠ 0, y ≠ 0, then the value of DPtable (x, y) is calculated according to following manner, and is recorded each grid and be derived from
Where to direction is recorded in the table Pathtable of path:
Firstly, y is traversed from 1 to n-1 when x=1,
The value for enabling K1, K2, K3 is respectively DPtable (x-1, y-1), DPtable (x-1, y), DPtable (x, y-1)
Value, then the value of DPtable (x, y) is equal to the value of Min (K1, K2, K3)+Datatable (x, y), and if K1/K2/K3 is minimum
Value, then the value of Pathtable (x, y) is A/B/C；
Similarly, when x=2,3 ... ..., n-1, y is traversed from 1 to m-1 respectively, is repeated the above process；
Step S22: according to path table Pathtable calculated result, the path of Pathtable is acquired, calculation is such as
Under:
X is from n -1 to 0 and y is from m -1 to 0 for traversal,
If the value of Pathtable (x, y) is A, x subtracts 1, and y subtracts 1, and stores x at this time, y value to (Rx,Ty) in；
If the value of Pathtable (x, y) is B, x subtracts 1；
If the value of Pathtable (x, y) is C, y subtracts 1.
Compared to the prior art, the invention has the following advantages: the method for the present invention is in aspect ratio clock synchronization, with infrared ray
It rotates with the length, angle, previous line segment of the line segment of visible light contour of object to the rotation angle of the line segment, line segment rotation
Rotation angle to latter line segment establishes two-dimensional table as comparison condition, and using Dynamic Programming, calculates the phase of two profiles
Like degree, finally according to the point compared, the homography matrix Homographymatrix suitable for each profile is calculated separately, with
This matrix uses perspective projection to the image of infrared ray object respectively, finally positions the image after conversion to similar degree
On highest visible light object, summation is at a complete image.This method be to handle visible light and infrared image from
It dynamic positioning and coincides, enables the more than one human body of infrared image automatic comparison, infrared ray is navigated into visible image
Upper correct position, pedestrian's temperature of going forward side by side calculate.
Detailed description of the invention
Fig. 1 is the background of definition.
Fig. 2 is the visible light and infrared image read.
Fig. 3 is visible light and infrared ray mobile object profile.
Fig. 4 is the Datatable of one embodiment of the invention.
Fig. 5 is result (a) DPtable, (b) Pathtable based on Fig. 4.
Fig. 6 is the path of Pathtable.
Fig. 7 is final comparison result figure.
Fig. 8 is the result figure that coincides.
Specific embodiment
With reference to the accompanying drawing, technical solution of the present invention is specifically described.
A kind of real-time body's temperature rapid detection method of the invention, firstly, obtaining the object of visible light and infrared image
Simplification profile after, with Dynamic Programming carry out profile intersection compare, then through perspective projection conversion infrared ray object is changed
It is bonded to and similarly spends on highest visible light object, pedestrian's temperature of going forward side by side calculates, and the specific implementation steps are as follows:
Step S1, image is absorbed by infrared camera and visible light photography machine, obtains infrared image and visible light
Image；Then back-packing is gone to obtain mobile object profile using Gauss visible image；By the color space of infrared image from
RGB goes to HSV, obtains mobile object profile according to formula (1)
Wherein, F (x, y) is prospect image, and H (x, y) is form and aspect channel, and x, y are image coordinate；
Step S2, infrared image is obtained with after the profile of each mobile object in visible image, is forced using polygon
Nearly method approaches profile, then and the parameter of each line segment in profile is calculated according to simplification profile, comprising: the angle of line segment
Degree A, the length L of line segment, previous line segment angle rotate the angle of rotation angle PR to the angle of current line segment, current line segment
It rotates to the rotation angle NR of the angle of latter line segment, line segment two-end-point is defined as a and b, then a parameter calculation formula such as (2)
Shown in~(5):
PR=| Current Segment Angle-Previous Segment Angle | (4)
NR=| Next Segment Angle-Current Segmemt Angle | (5)
Wherein, a, b are the two-end-point for forming line segment, and x, y are image coordinate；
Then profile is compared using Dynamic Programming DP, establishes the data form Datatable of a two-dimensional array, table is big
Small is visible light mobile object line segment quantity × infrared ray mobile object line segment quantity, and the value in table is respectively that visible light moves
The corresponding line segment of animal body profile compared with the corresponding line segment of infrared ray mobile object profile after difference value, compare formula
Such as (6)
Wherein, formula (6) indicates that current computing object is the value on xth column, the column y in Datatable, that is, compares visible light
The length L, previous of y-th of line segment of mobile object R and the angle A of line segment on the xth line segment of infrared ray mobile object T, line segment
The angle of line segment is rotated to the angle of the rotation angle PR of the angle of current line segment, current line segment and is rotated to the angle of latter line segment
The value of rotation angle NR this four differences, W1, W2, W3 and W4 are corresponding weight；
Then according to data form, using Dynamic Programming DP with mobile object profile is two-by-two the total poor of one group of calculating profile
Different value；
Step S3: being that each mobile object profile calculates a homography matrix according to comparison result, by the movement of infrared ray
After object individually takes out, infrared ray mobile object is converted into visible light mobile object using perspective conversion, finally by infrared ray
Mobile object is fused on visible light mobile object, and pedestrian's temperature of going forward side by side calculates.
In step S2 of the present invention, using Dynamic Programming DP with mobile object profile is two-by-two the total poor of one group of calculating profile
The specific implementation steps are as follows for different value:
Step S21: DP table DPtable is initialized according to following four conditional definitions, wherein DPtable (x, y) is indicated
The value of DPtable xth column, the column y, it is seen that light mobile object R line segment quantity is n, infrared ray mobile object T line segment quantity is
M, and with A, B, C respectively represent three Fang Xiang ↖, ←, ↑, X then represent without tracking:
(1) if x=0, y=0, then the value of DPtable (0,0) be equal to Datatable (0,0) value, Pathtable (0,
0) value is X；
(2) if x=0, y ≠ 0, then the value of DPtable (0, y) is equal to DPtable (0, y-1)+Datatable's (0, y)
Value, the value of Pathtable (0, y) are C；
(3) if x ≠ 0, y=0, then the value of DPtable (x, 0) is equal to DPtable (x-1,0)+Datatable's (x, 0)
Value, the value of Pathtable (x, 0) are B；
(4) if x ≠ 0, y ≠ 0, then the value of DPtable (x, y) is calculated according to following manner, and is recorded each grid and be derived from
Where to direction is recorded in the table Pathtable of path:
Firstly, y is traversed from 1 to n-1 when x=1,
The value for enabling K1, K2, K3 is respectively DPtable (x-1, y-1), DPtable (x-1, y), DPtable (x, y-1)
Value, then the value of DPtable (x, y) is equal to the value of Min (K1, K2, K3)+Datatable (x, y), and if K1/K2/K3 is minimum
Value, then the value of Pathtable (x, y) is A/B/C；
Similarly, when x=2,3 ... ..., n-1, y is traversed from 1 to m-1 respectively, is repeated the above process；
Step S22: according to path table Pathtable calculated result, the path of Pathtable is acquired, calculation is such as
Under:
X is from n -1 to 0 and y is from m -1 to 0 for traversal,
If the value of Pathtable (x, y) is A, x subtracts 1, and y subtracts 1, and stores x at this time, y value to (Rx,Ty) in；
If the value of Pathtable (x, y) is B, x subtracts 1；
If the value of Pathtable (x, y) is C, y subtracts 1.
The following are specific implementation processes of the invention.
The method of the present invention obtains mobile object in image using infrared camera and visible light photography machine pick-up image
Afterwards, the similarity between contour of object is calculated using Dynamic Programming, specific as follows:
1, background, such as Fig. 1 are defined.
2, infrared ray and visible image are read, such as Fig. 2 then goes back-packing to obtain movement visible image using Gauss
Contour of object；HSV is gone to from RGB by the color space of image to infrared image, is taken out channel (Hue), according to formula (1)
Mobile object profile is obtained, result such as Fig. 3 is obtained.
Wherein, F (x, y) is prospect image, and H (x, y) is form and aspect channel, and x, y are image coordinate；
3, the profile for obtaining each mobile object, will be taken turns using polygonous approximation Douglas-Peuckeralgorithm
Exterior feature is approached, then to calculate the parameter of each line segment in profile: the angle (Angle, A) of line segment, line according to simplification profile
Length (Length, L), the angle of previous line segment of section are rotated to the rotation angle of the angle of the line segment
The angle of (PreviousrotationAngle, PR), the line segment rotates the rotation angle of the angle to latter line segment
Line segment two-end-point is defined as a and b, parameter calculation formula such as (2)~(5) by (NextrotationAngle, NR).
PR=| Current Segment Angle-Previous Segment Angle | (4)
NR=| Next Segment Angle-Current Segment Angle | (5)
Wherein, a, b are the two-end-point for forming line segment, and x, y are image coordinate；
Then profile is compared using Dynamic Programming (Dynamicprogramming, abbreviation DP), establishes a two-dimensional array,
Table size is visible light object line segment quantity × infrared ray object line segment quantity, and the value in table is respectively visible light object
Certain line segment of profile compared with certain line segment of infrared ray contour of object after difference value, compare formula such as (6), this table is
For data form (Data table).
Wherein, formula (6) indicates that current computing object is the value on xth column, the column y in Datatable, that is, compares visible light
The length L, previous of y-th of line segment of mobile object R and the angle A of line segment on the xth line segment of infrared ray mobile object T, line segment
The angle of line segment is rotated to the angle of the rotation angle PR of the angle of current line segment, current line segment and is rotated to the angle of latter line segment
The value of rotation angle NR this four differences, W1, W2, W3 and W4 are corresponding weight.
Then according to data form, DP is used according to following steps (Step1~Step3), two-by-two one group of calculating wheel of profile
Wide total variances value, below it will be seen that light is referred to as R, infrared ray is referred to as T.
Step1. DP table (DPtable) is initialized, according to the initial value of following four condition definition data tables:
Ifx=0andy=0, thenDPtable (0,0) ← Datatable (0,0)
Ifx=0andy ≠ 0, thenDPtable (0, y) ← DPtable (0, y-1)+Datatable (0, y)
Ifx ≠ 0andy=0, thenDPtable (x, 0) ← DPtable (x-1,0)+Datatable (x, 0)
Ifx≠0andy≠0,thenDPtable(x,0)←followthenextrule(Step2).
Above-mentioned " ← " represents assignment；
Fig. 4 is to assume data form, assists process parsing:
Step2. DPtable is calculated, i.e., when x ≠ 0 and y ≠ 0, calculates DPtable (x, y) according to following algorithm and records every
Where a grid is derived to direction to be recorded in path table (Pathtable).Wherein visible light mobile object R has n item
Line segment, infrared ray mobile object T have m line segment, A, B, C here respectively represent three Fang Xiang ↖, ←, ↑, DPtable (x,
Y) value on DPtable xth column, the column y is indicated:
By the above process, according to the Datatable of Fig. 4, the DPtable and Pathtable of Fig. 5 can be acquired:
Step3. comparison result is tracked according to Pathtable, acquires the path of the Pathtable of Fig. 6, tracing algorithm is such as
Under:
Final comparison result such as Fig. 7.
4. being that each profile calculates a Homographymatrix according to comparison result, the object of infrared ray is individually taken
After out, infrared ray object is converted into visible light object using perspective conversion, infrared ray object is finally fused to visible light object
On body, pedestrian's temperature of going forward side by side is calculated, the result that coincides such as Fig. 8.
The above are preferred embodiments of the present invention, all any changes made according to the technical solution of the present invention, and generated function is made
When with range without departing from technical solution of the present invention, all belong to the scope of protection of the present invention.
Claims (3)
1. a kind of real-time body's temperature rapid detection method, which is characterized in that firstly, obtaining the object of visible light and infrared image
Simplification profile after, with Dynamic Programming carry out profile intersection compare, then through perspective projection conversion infrared ray object is changed
It is bonded to and similarly spends on highest visible light object, pedestrian's temperature of going forward side by side calculates.
2. a kind of real-time body's temperature rapid detection method according to claim 1, which is characterized in that this method specific implementation
Steps are as follows:
Step S1, image is absorbed by infrared camera and visible light photography machine, obtains infrared image and visible image；
Then back-packing is gone to obtain mobile object profile using Gauss visible image；The color space of infrared image is turned from RGB
To HSV, mobile object profile is obtained according to formula (1)
Wherein, F (x, y) is prospect image, and H (x, y) is form and aspect channel, and x, y are image coordinate；
Step S2, infrared image is obtained with after the profile of each mobile object in visible image, uses polygonous approximation
Profile is approached, then and according to simplification profile calculate profile in each line segment parameter, comprising: the angle A of line segment, line
The length L of section, the angle of previous line segment are rotated to the angle of the rotation angle PR of the angle of current line segment, current line segment and are rotated to rear
Line segment two-end-point is defined as a and b by the rotation angle NR of the angle of one line segment, then a parameter calculation formula such as (2)~(5) are shown:
PR=| Current Segme nt Angle-Previous Segme ntAngle | (4)
NR=| Next Segme nt Angle-Current Segme nt Angle | (5)
Wherein, a, b are the two-end-point for forming line segment, and x, y are image coordinate；
Then profile is compared using Dynamic Programming DP, establishes the data form Data table an of two-dimensional array, table size
For visible light mobile object line segment quantity × infrared ray mobile object line segment quantity, the value in table is respectively visible light motive objects
The corresponding line segment of body profile compared with the corresponding line segment of infrared ray mobile object profile after difference value, compare formula such as (6)
Wherein, formula (6) indicates that current computing object is the value on xth column, the column y in Data table, that is, compares visible light shifting
The angle A of line segment, the length L of line segment, previous line on y-th of line segment of animal body R and the xth line segment of infrared ray mobile object T
The angle of section rotates to the angle of the rotation angle PR of the angle of current line segment, current line segment the rotation for rotating the angle to latter line segment
The difference of this four values of corner NR, W1, W2, W3 and W4 are corresponding weight；
Then according to data form, total variances of the Dynamic Programming DP with mobile object profile two-by-two for one group of calculating profile are used
Value；
Step S3: being that each mobile object profile calculates a homography matrix according to comparison result, by the mobile object of infrared ray
After individually taking out, infrared ray mobile object is converted into visible light mobile object using perspective conversion, it is finally that infrared ray is mobile
Object is fused on visible light mobile object, and pedestrian's temperature of going forward side by side calculates.
3. a kind of real-time body's temperature rapid detection method according to claim 2, which is characterized in that in step S2, use
Dynamic Programming DP with mobile object profile two-by-two be one group of calculating profile total variances value the specific implementation steps are as follows:
Step S21: DP table DP table is initialized according to following four conditional definitions, wherein DP table (x, y) indicates DP
The value of table xth column, the column y, it is seen that light mobile object R line segment quantity is n, infrared ray mobile object T line segment quantity is m, and
With A, B, C respectively represent three Fang Xiang ↖, ←, ↑, X then represent without tracking:
(1) if x=0, y=0, then the value of DP table (0,0) is equal to the value of Data table (0,0), Path table (0,0)
Value be X；
(2) if x=0, y ≠ 0, then the value of DP table (0, y) is equal to DP table (0, y-1)+Data table's (0, y)
Value, the value of Path table (0, y) are C；
(3) if x ≠ 0, y=0, then the value of DP table (x, 0) is equal to DP table (x-1,0)+Data table's (x, 0)
Value, the value of Path table (x, 0) are B；
(4) if x ≠ 0, y ≠ 0, then the value of DP table (x, y) is calculated according to following manner, and record each grid be derived from where
To direction is recorded in the table Path table of path:
Firstly, y is traversed from 1 to n-1 when x=1,
The value for enabling K1, K2, K3 is respectively DP table (x-1, y-1), DP table (x-1, y), DP table (x, y-1)
Value, then the value of DP table (x, y) is equal to the value of Min (K1, K2, K3)+Data table (x, y), and if K1/K2/K3 is most
Small value, then the value of Path table (x, y) is A/B/C；
Similarly, when x=2,3 ... ..., n-1, y is traversed from 1 to m-1 respectively, is repeated the above process；
Step S22: according to path table Path table calculated result, the path of Path table is acquired, calculation is as follows:
X is from n -1 to 0 and y is from m -1 to 0 for traversal,
If the value of Path table (x, y) is A, x subtracts 1, and y subtracts 1, and stores x at this time, y value to (Rx,Ty) in；
If the value of Path table (x, y) is B, x subtracts 1；
If the value of Path table (x, y) is C, y subtracts 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810399016.2A CN109029779B (en) | 2018-04-28 | 2018-04-28 | Real-time human body temperature rapid detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810399016.2A CN109029779B (en) | 2018-04-28 | 2018-04-28 | Real-time human body temperature rapid detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109029779A true CN109029779A (en) | 2018-12-18 |
| CN109029779B CN109029779B (en) | 2020-02-14 |
Family
ID=64629614
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810399016.2A Active CN109029779B (en) | 2018-04-28 | 2018-04-28 | Real-time human body temperature rapid detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109029779B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111174937A (en) * | 2020-02-20 | 2020-05-19 | 中国科学院半导体研究所 | Scanning type infrared body temperature detection device and method based on photoelectric cabin |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004013474A1 (en) * | 2002-07-31 | 2004-02-12 | Volkswagen Aktiengesellschaft | Method for the applied adaptation of the control of a motor and control of a motor that is obtained according to said method |
| CN1530639A (en) * | 2003-03-17 | 2004-09-22 | 财团法人工业技术研究院 | Thermometer with integrated image display |
| US20040208230A1 (en) * | 2003-04-16 | 2004-10-21 | Tzong-Sheng Lee | Thermometer with image display |
| CN102884841A (en) * | 2010-05-05 | 2013-01-16 | 摩托罗拉移动有限责任公司 | Mobile device with temperature sensing capability and method of operating same |
| JP2016103786A (en) * | 2014-11-28 | 2016-06-02 | 日立マクセル株式会社 | Imaging system |
| CN106919806A (en) * | 2017-04-27 | 2017-07-04 | 刘斌 | A kind of human body monitoring method, device and system and computer readable storage devices |
| CN106981077A (en) * | 2017-03-24 | 2017-07-25 | 中国人民解放军国防科学技术大学 | Infrared image and visible light image registration method based on DCE and LSS |
| CN107595254A (en) * | 2017-10-17 | 2018-01-19 | 黄晶 | A kind of infrared ray health monitor method and system |
| WO2018025404A1 (en) * | 2016-08-05 | 2018-02-08 | 株式会社オプティム | Diagnosis device |
| CN108549874A (en) * | 2018-04-19 | 2018-09-18 | 广州广电运通金融电子股份有限公司 | A kind of object detection method, equipment and computer readable storage medium |
-
2018
- 2018-04-28 CN CN201810399016.2A patent/CN109029779B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004013474A1 (en) * | 2002-07-31 | 2004-02-12 | Volkswagen Aktiengesellschaft | Method for the applied adaptation of the control of a motor and control of a motor that is obtained according to said method |
| CN1530639A (en) * | 2003-03-17 | 2004-09-22 | 财团法人工业技术研究院 | Thermometer with integrated image display |
| US20040208230A1 (en) * | 2003-04-16 | 2004-10-21 | Tzong-Sheng Lee | Thermometer with image display |
| CN102884841A (en) * | 2010-05-05 | 2013-01-16 | 摩托罗拉移动有限责任公司 | Mobile device with temperature sensing capability and method of operating same |
| JP2016103786A (en) * | 2014-11-28 | 2016-06-02 | 日立マクセル株式会社 | Imaging system |
| WO2018025404A1 (en) * | 2016-08-05 | 2018-02-08 | 株式会社オプティム | Diagnosis device |
| CN106981077A (en) * | 2017-03-24 | 2017-07-25 | 中国人民解放军国防科学技术大学 | Infrared image and visible light image registration method based on DCE and LSS |
| CN106919806A (en) * | 2017-04-27 | 2017-07-04 | 刘斌 | A kind of human body monitoring method, device and system and computer readable storage devices |
| CN107595254A (en) * | 2017-10-17 | 2018-01-19 | 黄晶 | A kind of infrared ray health monitor method and system |
| CN108549874A (en) * | 2018-04-19 | 2018-09-18 | 广州广电运通金融电子股份有限公司 | A kind of object detection method, equipment and computer readable storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111174937A (en) * | 2020-02-20 | 2020-05-19 | 中国科学院半导体研究所 | Scanning type infrared body temperature detection device and method based on photoelectric cabin |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109029779B (en) | 2020-02-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9911198B2 (en) | Method, system and apparatus for matching moving targets between camera views | |
| Sankaranarayanan et al. | Object detection, tracking and recognition for multiple smart cameras | |
| Hampapur et al. | Smart video surveillance: exploring the concept of multiscale spatiotemporal tracking | |
| Dame et al. | Second-order optimization of mutual information for real-time image registration | |
| Zhou et al. | A master-slave system to acquire biometric imagery of humans at distance | |
| Bilodeau et al. | Visible and infrared image registration using trajectories and composite foreground images | |
| Mendoza-Schrock et al. | Video image registration evaluation for a layered sensing environment | |
| Silveira et al. | Unified direct visual tracking of rigid and deformable surfaces under generic illumination changes in grayscale and color images | |
| Lou et al. | Image alignment by piecewise planar region matching | |
| Ellmauthaler et al. | A visible-light and infrared video database for performance evaluation of video/image fusion methods | |
| Guo et al. | Robust object matching for persistent tracking with heterogeneous features | |
| Jiang et al. | Thermal-inertial SLAM for the environments with challenging illumination | |
| Wu et al. | Real-time 3D road scene based on virtual-real fusion method | |
| CN109029779A (en) | A kind of real-time body's temperature rapid detection method | |
| Zhang et al. | Building a stereo and wide-view hybrid RGB/FIR imaging system for autonomous vehicle | |
| Hayet et al. | Robust incremental rectification of sports video sequences | |
| Zhang et al. | Build your own hybrid thermal/EO camera for autonomous vehicle | |
| Beleznai et al. | Multi-modal human detection from aerial views by fast shape-aware clustering and classification | |
| Lee et al. | Vehicle counting based on a stereo vision depth maps for parking management | |
| Song | Optimization of the Progressive Image Mosaicing Algorithm in Fine Art Image Fusion for Virtual Reality | |
| McCartney et al. | Image registration for sequence of visual images captured by UAV | |
| Zuo et al. | Algorithm for unmanned aerial vehicle aerial different-source image matching | |
| Belongie et al. | Structure from periodic motion | |
| Cao et al. | Video synchronization and its application to object transfer | |
| Yao et al. | An effective dual-fisheye lens stitching method based on feature points |
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 |