CN105352604A - Infrared temperature measurement system holder position calibration method based on visible light image registration - Google Patents

Infrared temperature measurement system holder position calibration method based on visible light image registration Download PDF

Info

Publication number
CN105352604A
CN105352604A CN201510733755.7A CN201510733755A CN105352604A CN 105352604 A CN105352604 A CN 105352604A CN 201510733755 A CN201510733755 A CN 201510733755A CN 105352604 A CN105352604 A CN 105352604A
Authority
CN
China
Prior art keywords
visible light
image
cloud terrace
temperature measurement
infrared temperature
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201510733755.7A
Other languages
Chinese (zh)
Inventor
崔昊杨
王佳林
王超群
刘璨
许永鹏
曾俊冬
杨俊杰
唐忠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai University of Electric Power
University of Shanghai for Science and Technology
Original Assignee
Shanghai University of Electric Power
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai University of Electric Power filed Critical Shanghai University of Electric Power
Priority to CN201510733755.7A priority Critical patent/CN105352604A/en
Publication of CN105352604A publication Critical patent/CN105352604A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/80—Calibration

Abstract

The invention relates to an infrared temperature measurement system holder position calibration method based on visible light image registration. The method comprises the following steps: (1) pre-acquiring a standard image of a preset position through a visible light video probe, and storing the standard image as a template image; (2) acquiring a current image of the preset position through the visible light video probe when a holder returns to the preset position again, and calling the current image a target image; (3) acquiring the position deviation between the template image and the target image, judging whether the position deviation is greater than a predetermined threshold, executing step (4) if the position deviation is greater than the predetermined threshold, or returning to step (2); and (4) generating a compensation parameter through a holder controller according to the position deviation, making the holder rotate according to the compensation parameter, and calibrating the holder to make the holder return to the preset position. Compared with the prior art, the method of the invention has the advantages of less repeated operation, high image matching speed, effective realization of temperature measurement position correction, and the like.

Description

Based on the infrared temperature measurement system The Cloud Terrace position calibration method of visible light image registration
Technical field
The present invention relates to a kind of infrared temperature measurement system position calibration method, especially relate to a kind of infrared temperature measurement system The Cloud Terrace position calibration method based on visible light image registration.
Background technology
Along with the fast development of video monitoring system, the The Cloud Terrace of band presetting bit function uses more and more extensive, is particularly widely applied in infrared temperature measurement system.Can quickly positioning target by the built-in menu setting presetting bit of The Cloud Terrace, ideally, the scanning temperature measuring system be made up of the temperature measurer of The Cloud Terrace and load can carry out temperature detection to remote target, realizes the repetitive scanning temperature measuring of The Cloud Terrace to multiple target point by arranging presetting bit.But because the presetting bit function of The Cloud Terrace position deviation can occur after The Cloud Terrace long-play, even if use reset self-check program to reduce The Cloud Terrace itself run the position deviation brought, but inevitably will there is at stiff end the phenomenon that structure firmware expands with heat and contract with cold in scanning system, make system monitoring to point for measuring temperature depart from actual target locations, cause the precision of presetting bit not high, the requirement that some occasions accurately control can not be met.
People adopt this deviation of a lot of method corrections, as carried out images match etc.Method at present for images match mainly contains based on gradation of image correlation technique, based on characteristics of image method, based on artificial intelligence approaches such as artificial neural network and genetic algorithms.Wherein, the matching algorithm based on gradation of image is simple, and matching accuracy rate is high, but calculated amount is large, is unfavorable for real-time process.To grey scale change, rotation, deformation and to block etc. more responsive; Method calculated amount based on characteristics of image is relatively little, and to grey scale change, deformation and blocked good adaptability, but matching precision is not high; Method development based on the artificial intelligence such as neural network, genetic algorithm is more late, and algorithm is also immature.
Summary of the invention
Object of the present invention is exactly that cradle head preset positions function in order to solve above-mentioned infrared temperature measurement system position deviation can occur after long-play, even if use reset self-check program, still there is the problem of the impact that stiff end expands with heat and contract with cold, provide that a kind of repetitive operation is few, picture match speed is high, effectively realize the infrared temperature measurement system The Cloud Terrace position calibration method based on visible light image registration that temperature measurement location corrects.
Object of the present invention can be achieved through the following technical solutions:
Based on an infrared temperature measurement system The Cloud Terrace position calibration method for visible light image registration, the method comprises the following steps:
1) popped one's head in by visible light video and gather the standard picture of presetting bit in advance, and be stored as template image;
2) when The Cloud Terrace gets back to presetting bit again, by the present image of visible light video probe acquires presetting bit, this present image is called target image;
3) obtain the position deviation between template image and target image, judge whether this position deviation is greater than predetermined threshold, if so, then perform step 4), if not, then return step 2);
4) cradle head controllor produces compensating parameter according to described position deviation, controls cloud platform rotation, calibrating tripod head presetting bit by this compensating parameter.
Described visible light video probe is parallel with infrared temperature probe to be fixed on The Cloud Terrace.
Described step 3) in, obtain the position deviation between template image and target image by maximum cross correlation algorithm.
Described maximum cross correlation algorithm adopts maximum fast correlation algorithm, and when searching for relevant matches point, adopts thick coupling and essence coupling to determine final match point simultaneously.
Described step 4) in, compensating parameter obtains according to the relation of described position deviation and The Cloud Terrace actual motion distance.
Compared with prior art, the present invention has the following advantages:
(1) visible light video probe, infrared thermometer, scanning The Cloud Terrace, cradle head controllor are combined by the present invention, utilize the image information of visible light video probe acquires impact point, and contrast the image and actual target point image difference that collect, position deviation is obtained by maximum cross correlation algorithm, in this, as controlling the level of The Cloud Terrace, the foundation of vertical movement calibration, realize the calibration of presetting bit, there is operation and calculate simple, consuming time less, the advantage such as practical function.
(2) adopt maximum cross-correlation coefficient algorithm to carry out images match to template image and target image, by simplifying the computing formula of related coefficient, when not affecting matching precision, reaching and reducing calculation of correlation calculated amount.
(3) the present invention adopts thick coupling and essence coupling two processes, effectively improves matching speed.
Accompanying drawing explanation
Fig. 1 is schematic flow sheet of the present invention;
Fig. 2 is position deviation of the present invention calibration process flow diagram;
Fig. 3 preset positions of camera deviation calibration process flow diagram;
Fig. 4 slightly mates schematic diagram;
Fig. 5 is essence coupling schematic diagram.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.The present embodiment is implemented premised on technical solution of the present invention, give detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
The embodiment of the present invention provides a kind of infrared temperature measurement system The Cloud Terrace position calibration method based on visible light image registration, the method is calibrated the presetting bit of The Cloud Terrace by visible light video probe, infrared temperature measurement system is transform as and is made up of visible video probe, infrared thermometer, scanning The Cloud Terrace and cradle head controllor, wherein, visible light video probe is parallel with infrared temperature probe to be fixed on The Cloud Terrace, realizes interlock by rotary head.This method obtains template image by visible light video probe, and The Cloud Terrace leaves presetting bit and again gets back to the target image of presetting bit, then the position deviation of template image and target image is analyzed by maximum cross correlation algorithm, and utilize cradle head controllor to control the rotation of The Cloud Terrace, The Cloud Terrace is made to get back to presetting bit fast, in order to better control The Cloud Terrace precision, user can according to current presetting bit call instruction obtain its target position data and this operational process obtain The Cloud Terrace physical location and upgrade compensating parameter in the compensating module of position, thus the problem of position deviation after solving The Cloud Terrace long-play.
As shown in Figure 1, the method specifically comprises the following steps:
Step S101, is popped one's head in by visible light video and gathers the standard picture of presetting bit in advance, and be stored as template image;
Step S102, The Cloud Terrace gets back to the presetting bit of target;
Step S103, by the present image of visible light video probe acquires presetting bit, is called target image by this present image;
Step S104, obtains the position deviation between template image and target image;
Step S105, cradle head controllor produces compensating parameter according to position deviation;
Step S106, controls cloud platform rotation by this compensating parameter, calibrating tripod head presetting bit.
As shown in Figure 2, position deviation calibration flow process is specially:
Step S201, The Cloud Terrace gets back to the presetting bit of target;
Step S202, by the present image of visible light video probe acquires presetting bit, is called target image by this present image;
Step S203, is analyzed the position deviation of template image and target image, determines the centre coordinate of maximum match point, subtract each other with the centre coordinate of template image, just can obtain the position deviation of target image and template image by maximum cross correlation algorithm;
Step S204, judges whether this position deviation is greater than predetermined threshold, and if so, then cradle head controllor produces compensating parameter according to position deviation, and control cloud platform rotation by this compensating parameter, calibrating tripod head gets back to presetting bit, if not, then returns step S202.
Obtain compensating parameter according to position deviation and the actual range between measured target and infrared temperature measurement system, control cloud platform rotation according to compensating parameter setting compensation module, realize the calibration to infrared temperature measurement system.As shown in Figure 3, detect The Cloud Terrace by position transducer and run the physical location put in place, calculate the position deviation between the target location of presetting bit The Cloud Terrace and described The Cloud Terrace physical location, the relation calculating this deviation and actual motion distance obtains compensating parameter, according to this compensating parameter desired location compensating module.In follow-up cradle head preset positions runs and controls, call the compensation rate in compensating module, and obtained compensation rate and The Cloud Terrace target location are added deliver to controller and be used for controlling The Cloud Terrace and run.Expand with heat and contract with cold and frictional resistance impact because The Cloud Terrace still exists stiff end in operational process, only have the corresponding compensating parameter of adjustment, higher running precision can be obtained.
In the present embodiment, calculating template image and target image being carried out to position deviation adopts the maximum cross correlation algorithm of images match.This algorithm is a kind of base conditioning method of computer picture science, is specially:
If f (x, y) is a width size is the target image of M*N, be designated as A, g (x, y) is the template image of a width m*n, is designated as B, finds out the sub-block matched with A according to relevant matches in B.
Use S x,yrepresent with (x, the y) sub-block for the upper left angle point A identical with B size in A, while also represent the matrix that this sub-block is corresponding, namely
S x,y(i,j)＝f(x+i-1,y+j-1)i＝1,2...,m；j＝1,2...,n(1)
ρ (x, y) represents S x,yrelated coefficient with B, is defined as follows:
ρ ( x , y ) = cov ( S x , y , B ) D x , y D - - - ( 2 )
Wherein D x,yfor S x,yvariance, D is the variance of B, cov (S x,y, B) and be S x,ywith the covariance of B; Thus
D x , y = 1 m n Σ i = 1 m Σ j = 1 n ( S x , y ( i , j ) - S x , y ‾ ) 2 - - - ( 3 )
D = 1 m n Σ i = 1 m Σ j = 1 n ( B ( i , j ) - B ‾ ) 2 - - - ( 4 )
cov ( S x , y , B ) = 1 m n Σ i = 1 m Σ j = 1 n ( S x , y ( i , j ) - S x , y ‾ ) ( B ( i , j ) - B ‾ ) - - - ( 5 )
Wherein with represent image S respectively x,ywith the gray average of B.
If ρ (x, y) very greatly or very close to 1, then shows that image mates with image A in this point.
Analysis can obtain, containing a large amount of repetitive operation in the calculating of consecutive point, due to S x, (y+1)subgraph S x,ymove to right subgraph corresponding to the position of row in A, such S x, (y+1)front n-1 row be just in time S x,yrear n-1 row, at calculating S x, (y+1)time can utilize S x,yvalue reduce calculated amount.
Σ i = 1 m Σ j = 1 n S x , y + 1 ( i , j ) = Σ i = 1 m Σ j = 1 n S x , y ( i , j ) + Σ i = x x + m - 1 [ S ( i , y + n ) - S ( i , y ) ] - - - ( 6 )
Σ i = 1 m Σ j = 1 n S 2 x , y + 1 ( i , j ) = Σ i = 1 m Σ j = 1 n S 2 x , y ( i , j ) + Σ i = x x + m - 1 [ S 2 ( i , y + n ) - S 2 ( i , y ) ] - - - ( 7 )
Σ i = 1 m Σ j = 1 n S x + 1 , y ( i , j ) = Σ i = 1 m Σ j = 1 n S x , y ( i , j ) + Σ i = y y + n - 1 [ S ( x + m , i ) - S ( x , i ) ] - - - ( 8 )
Σ i = 1 m Σ j = 1 n S 2 x + 1 , y ( i , j ) = Σ i = 1 m Σ j = 1 n S 2 x , y ( i , j ) + Σ i = y y + n - 1 [ S 2 ( x + m , i ) - S 2 ( x , i ) ] - - - ( 9 )
Similar, at calculating D x, (y+1)time can utilize D x,yvalue reduce calculated amount.Namely for a width gray level image, following recursion formula is had:
D x , ( y + 1 ) = D x , y + T 2 - T 1 2 - 2 T 1 S x , y ‾ - - - ( 10 )
D ( x + 1 ) , y = D x , y + T ~ 2 - T ~ 1 2 - 2 T ~ 1 S x , y ‾ - - - ( 11 )
T 1 = 1 m n Σ i = x x + m - 1 [ f ( i , y + n ) - f ( i , y ) ] T 2 = 1 m n Σ i = x x + m - 1 [ f 2 ( i , y + n ) - f 2 ( i , y ) ] - - - ( 12 )
T ~ 1 = 1 m n Σ i = y y + n - 1 [ f ( x + m , i ) - f ( x , i ) ] T ~ 2 = 1 m n Σ i = y y + n - 1 [ f 2 ( x + m , i ) - f 2 ( x , i ) ] - - - ( 13 )
Compared with original variance definition, this fast algorithm makes D x, (y+1)calculated amount reduce n doubly, D (x+1), ycalculated amount reduce m doubly.By shortcut calculation above, a large amount of unnecessary repetitive operations can be omitted, improve arithmetic speed.If but calculate the point of all positions, need the individual ρ (x, y) of record (M-m) × (N-n), calculated amount is still very large, and therefore the present invention also improves in search relevant matches point.
1, slightly mate
Thick coupling is divided into two aspects: first aspect, gets rid of impossible region, and the correlation coefficient value in these regions is less than certain thresholding system (generally getting 0.2); Second aspect, sorts to the size of possible region according to correlation coefficient value, finds out several regions that correlation coefficient value is maximum, as the matching area of essence coupling.
In thick coupling, do not need in target figure a little all carry out the calculating of related coefficient, and only need to calculate a point every certain step-length, as shown in Figure 4.In thick coupling, if the related coefficient numerical value finding that there is a point has exceeded thresholding given in advance (generally getting 0.85), so last exact matching point is just in the region at this place.Thus terminate thick coupling in advance, enter essence coupling.
2, essence coupling
Need that several region is obtained to thick matching process and carry out essence coupling, and to result through line ordering, wherein the point of maximum correlation coefficient value is exactly last match point.What essence coupling adopted is right-angled intersection fast search process.Step-size in search is determined by the correlation coefficient value obtained last time, and the point that correlation coefficient value is large, step-size in search is little, otherwise step-size in search is then large.
First slightly to mate centered by the point obtained, with corresponding step-length, calculate four points on its cross direction respectively, as shown in Figure 5, according to the size of these four Point correlation coefficients, determine the priority of the next direction of search.In search next time, if the correlation coefficient value of first point calculated is greater than the correlation coefficient value of the last point calculated, then current search is complete, enters and searches for next time, otherwise according to the order of orientation preferentially level, calculate the value in another direction, if the value of four direction is all less than the value that last search obtains, step-size in search doubles, again search for, if the value of four direction is still less than and last searches for the value obtained, then last time Searching point, be exactly this region essence matching result.

Claims (5)

1., based on an infrared temperature measurement system The Cloud Terrace position calibration method for visible light image registration, it is characterized in that, the method comprises the following steps:
1) popped one's head in by visible light video and gather the standard picture of presetting bit in advance, and be stored as template image;
2) when The Cloud Terrace gets back to presetting bit again, by the present image of visible light video probe acquires presetting bit, this present image is called target image;
3) obtain the position deviation between template image and target image, judge whether this position deviation is greater than predetermined threshold, if so, then perform step 4), if not, then return step 2);
4) cradle head controllor produces compensating parameter according to described position deviation, controls cloud platform rotation, calibrating tripod head presetting bit by this compensating parameter.
2. the infrared temperature measurement system The Cloud Terrace position calibration method based on visible light image registration according to claim 1, is characterized in that, described visible light video probe is parallel with infrared temperature probe to be fixed on The Cloud Terrace.
3. the infrared temperature measurement system The Cloud Terrace position calibration method based on visible light image registration according to claim 1, is characterized in that, described step 3) in, obtain the position deviation between template image and target image by maximum cross correlation algorithm.
4. the infrared temperature measurement system The Cloud Terrace position calibration method based on visible light image registration according to claim 3, it is characterized in that, described maximum cross correlation algorithm adopts maximum fast correlation algorithm, and when searching for relevant matches point, adopt thick coupling and essence coupling to determine final match point simultaneously.
5. the infrared temperature measurement system The Cloud Terrace position calibration method based on visible light image registration according to claim 1, is characterized in that, described step 4) in, compensating parameter obtains according to the relation of described position deviation and The Cloud Terrace actual motion distance.
CN201510733755.7A 2015-11-02 2015-11-02 Infrared temperature measurement system holder position calibration method based on visible light image registration Pending CN105352604A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510733755.7A CN105352604A (en) 2015-11-02 2015-11-02 Infrared temperature measurement system holder position calibration method based on visible light image registration

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510733755.7A CN105352604A (en) 2015-11-02 2015-11-02 Infrared temperature measurement system holder position calibration method based on visible light image registration

Publications (1)

Publication Number Publication Date
CN105352604A true CN105352604A (en) 2016-02-24

Family

ID=55328613

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510733755.7A Pending CN105352604A (en) 2015-11-02 2015-11-02 Infrared temperature measurement system holder position calibration method based on visible light image registration

Country Status (1)

Country Link
CN (1) CN105352604A (en)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106020240A (en) * 2016-05-25 2016-10-12 南京安透可智能系统有限公司 Holder control system of autonomous homing calibration
CN106289182A (en) * 2016-07-14 2017-01-04 济南中维世纪科技有限公司 A kind of by The Cloud Terrace camera from the method for dynamic(al) correction presetting bit
CN108279708A (en) * 2017-12-31 2018-07-13 深圳市秦墨科技有限公司 A kind of holder automatic calibrating method, device and holder
CN108428224A (en) * 2018-01-09 2018-08-21 中国农业大学 Animal body surface temperature checking method and device based on convolutional Neural net
CN108932732A (en) * 2018-06-21 2018-12-04 浙江大华技术股份有限公司 A kind of method and device obtaining monitoring object data information
CN109313439A (en) * 2017-07-28 2019-02-05 深圳市大疆创新科技有限公司 Holder method for testing reliability and device
CN109885105A (en) * 2016-12-30 2019-06-14 深圳市大疆灵眸科技有限公司 Cloud platform control method, device and holder
CN110765932A (en) * 2019-10-22 2020-02-07 北京商海文天科技发展有限公司 Scene change sensing method
CN111030750A (en) * 2019-10-09 2020-04-17 长飞光纤光缆股份有限公司 Probe registration method and system of multimode fiber DMD test equipment
CN111381579A (en) * 2018-12-30 2020-07-07 浙江宇视科技有限公司 Cloud deck fault detection method and device, computer equipment and storage medium
CN111982304A (en) * 2020-08-25 2020-11-24 南方电网调峰调频发电有限公司 Infrared temperature measurement compensation method and video temperature measurement composite sensor
CN113865712A (en) * 2021-08-02 2021-12-31 国网安徽省电力有限公司安庆供电公司 JP regulator cubicle temperature monitoring system
CN115914792A (en) * 2022-12-22 2023-04-04 长春理工大学 Real-time multidimensional imaging self-adaptive adjustment system and method based on deep learning
CN116309569A (en) * 2023-05-18 2023-06-23 中国民用航空飞行学院 Airport environment anomaly identification system based on infrared and visible light image registration

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090278926A1 (en) * 2006-06-19 2009-11-12 Advantest Corporation Calibration method of electronic device test apparatus
US20110013232A1 (en) * 2009-07-16 2011-01-20 Fuji Xerox Co., Ltd. Image processing device, image processing system, image processing method and computer readable medium
CN102937816A (en) * 2012-11-22 2013-02-20 四川华雁信息产业股份有限公司 Method and device for calibrating preset position deviation of camera
CN103607540A (en) * 2013-12-02 2014-02-26 南京南自信息技术有限公司 Method for improving presetting bit accuracy of pan-tilt camera

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090278926A1 (en) * 2006-06-19 2009-11-12 Advantest Corporation Calibration method of electronic device test apparatus
US20110013232A1 (en) * 2009-07-16 2011-01-20 Fuji Xerox Co., Ltd. Image processing device, image processing system, image processing method and computer readable medium
CN102937816A (en) * 2012-11-22 2013-02-20 四川华雁信息产业股份有限公司 Method and device for calibrating preset position deviation of camera
CN103607540A (en) * 2013-12-02 2014-02-26 南京南自信息技术有限公司 Method for improving presetting bit accuracy of pan-tilt camera

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
朱永松: ""基于相关系数的相关匹配算法的研究"", 《信号处理》 *
董安国: ""图像匹配最大互相关快速算法"", 《浙江万里学院学报》 *
郑远平: "《输变电设备红外紫外状态监测诊断技术》", 30 June 2013 *

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106020240A (en) * 2016-05-25 2016-10-12 南京安透可智能系统有限公司 Holder control system of autonomous homing calibration
CN106289182A (en) * 2016-07-14 2017-01-04 济南中维世纪科技有限公司 A kind of by The Cloud Terrace camera from the method for dynamic(al) correction presetting bit
CN109885105A (en) * 2016-12-30 2019-06-14 深圳市大疆灵眸科技有限公司 Cloud platform control method, device and holder
US11852958B2 (en) 2016-12-30 2023-12-26 Sz Dji Osmo Technology Co., Ltd. Gimbal control method, device, and gimbal
CN109885105B (en) * 2016-12-30 2022-04-19 深圳市大疆灵眸科技有限公司 Cloud deck control method and device and cloud deck
CN109313439A (en) * 2017-07-28 2019-02-05 深圳市大疆创新科技有限公司 Holder method for testing reliability and device
CN108279708B (en) * 2017-12-31 2021-08-27 深圳市越疆科技有限公司 Automatic cradle head calibration method and device and cradle head
CN108279708A (en) * 2017-12-31 2018-07-13 深圳市秦墨科技有限公司 A kind of holder automatic calibrating method, device and holder
CN108428224A (en) * 2018-01-09 2018-08-21 中国农业大学 Animal body surface temperature checking method and device based on convolutional Neural net
CN108428224B (en) * 2018-01-09 2020-05-22 中国农业大学 Animal body surface temperature detection method and device based on convolutional neural network
CN108932732A (en) * 2018-06-21 2018-12-04 浙江大华技术股份有限公司 A kind of method and device obtaining monitoring object data information
CN111381579A (en) * 2018-12-30 2020-07-07 浙江宇视科技有限公司 Cloud deck fault detection method and device, computer equipment and storage medium
CN111030750A (en) * 2019-10-09 2020-04-17 长飞光纤光缆股份有限公司 Probe registration method and system of multimode fiber DMD test equipment
CN110765932B (en) * 2019-10-22 2023-06-23 北京商海文天科技发展有限公司 Scene change sensing method
CN110765932A (en) * 2019-10-22 2020-02-07 北京商海文天科技发展有限公司 Scene change sensing method
CN111982304A (en) * 2020-08-25 2020-11-24 南方电网调峰调频发电有限公司 Infrared temperature measurement compensation method and video temperature measurement composite sensor
CN113865712A (en) * 2021-08-02 2021-12-31 国网安徽省电力有限公司安庆供电公司 JP regulator cubicle temperature monitoring system
CN115914792A (en) * 2022-12-22 2023-04-04 长春理工大学 Real-time multidimensional imaging self-adaptive adjustment system and method based on deep learning
CN116309569A (en) * 2023-05-18 2023-06-23 中国民用航空飞行学院 Airport environment anomaly identification system based on infrared and visible light image registration
CN116309569B (en) * 2023-05-18 2023-08-22 中国民用航空飞行学院 Airport environment anomaly identification system based on infrared and visible light image registration

Similar Documents

Publication Publication Date Title
CN105352604A (en) Infrared temperature measurement system holder position calibration method based on visible light image registration
CN110570449B (en) Positioning and mapping method based on millimeter wave radar and visual SLAM
CN105793892B (en) A kind of image processing method, device and picture pick-up device
US8384783B2 (en) Infrared camera and method for calculating output power value indicative of an amount of energy dissipated in an image view
CN110083157B (en) Obstacle avoidance method and device
US20080267453A1 (en) Method for estimating the pose of a ptz camera
CN103391430B (en) DSP (digital signal processor) based relevant tracking method and special device
CN105737990A (en) Detector temperature-based infrared image heterogeneity correction method and system
WO2021175281A1 (en) Infrared temperature measurement method, apparatus, and device, and storage medium
CN108680185A (en) Mobile robot gyroscope data correction method, device and equipment
CN108932732B (en) Method and device for acquiring data information of monitored object
KR20120043446A (en) Apparatus and method for detecting a location of vehicle and obstacle
US10643338B2 (en) Object detection device and object detection method
CN106101640A (en) Adaptive video sensor fusion method and device
KR101395544B1 (en) System and method for calibrating of object for measuring deformation structure
KR20140024746A (en) System and method for measuring deformation structure
CN107945166B (en) Binocular vision-based method for measuring three-dimensional vibration track of object to be measured
US20160171017A1 (en) Mobile positioning apparatus and positioning method thereof
US11682123B2 (en) Method for measuring humidity and electronic device using same
CN102622742B (en) Method and equipment for searching light spots and apertures of Hartmann wavefront detector
KR101583131B1 (en) System and method for providing offset calibration based augmented reality
CN114063024A (en) Calibration method and device of sensor, electronic equipment and storage medium
CN103365433A (en) Space mouse data processing method and mouse pointer control method
CN116228549B (en) Image stitching method, device, equipment and storage medium based on reinforcement learning
CN115655485B (en) Temperature measurement method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20160224