CN107992857A - A kind of high-temperature steam leakage automatic detecting recognition methods and identifying system - Google Patents
A kind of high-temperature steam leakage automatic detecting recognition methods and identifying system Download PDFInfo
- Publication number
- CN107992857A CN107992857A CN201711423014.4A CN201711423014A CN107992857A CN 107992857 A CN107992857 A CN 107992857A CN 201711423014 A CN201711423014 A CN 201711423014A CN 107992857 A CN107992857 A CN 107992857A
- Authority
- CN
- China
- Prior art keywords
- image
- recognition methods
- infrared
- automatic detecting
- edge
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/752—Contour matching
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/30—Transforming light or analogous information into electric information
- H04N5/33—Transforming infrared radiation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention discloses a kind of leakage automatic detecting recognition methods of high-temperature steam and identifying system.The recognition methods includes establishing an image library, for the visible ray for storing all inspection scene normal conditions and infrared double vision fusion figure;Using robot automatic detecting, with visible light camera and the realtime graphic of thermal imaging system shooting inspection point;Double vision convergence analysis processing is carried out with the realtime graphic to shooting, determines exception leak.The present invention can judge abnormal leak position in complicated high-temperature steam operation environment and can recognize that direction and the diffusion zone of steam leakage, and authentic data is provided for subsequent treatment.
Description
Technical field
The present invention relates to detection device, more particularly to a kind of leakage automatic detecting recognition methods of high-temperature steam and identification system
System.
Background technology
At present, the side that gas Leakage Detection technology is generally substantially judged using infrared or ultrasound examination means
Method.Chinese invention patent CN103775830A discloses a kind of high-temperature steam leak detection system and method, this article and elaborates profit
Leakage inspection is carried out with the method for the additional temperature sensing module array of infrared thermal imaging.Temperature in use in the detection method
The tested place's temperature of sensor assembly measurement, measures high-temperature targets with infrared thermal imaging, substantially judges source of leaks.
Above-mentioned existing detection technique has the following disadvantages:
1. degree of intelligence is not high, the direction of high-temperature steam leakage only cannot be accurately differentiated by temperature sensor and infrared imaging.
2. temperature sensor module array is proximity decision method, the directive property not had, for remote, have
The leak detection scene of interference cannot effectively be judged, not applied to.
3. gather in pipeline, or the scene of ultrasound environments complexity and do not apply to, it is impossible to the position of accurate judgement source of leaks and
Leakage situation, and under detection efficiency, can only be as the corresponding auxiliary judgment instrument of people, it is impossible to it is only instead of manpower to reach robot
Found the level of accurate inspection.
The content of the invention
The purpose of the present invention is in view of the above-mentioned drawbacks of the prior art, providing a kind of high-temperature steam leakage automatic detecting
Recognition methods and identifying system.
High-temperature steam proposed by the present invention leaks automatic detecting recognition methods, including:
Step S1:Sample image database is established, the visible ray and infrared double vision for storing all inspection point scene normal conditions melt
Close figure;
Step S2:Visible Light Camera and thermal imaging system are carried using robot, gathers the image of inspection point in real time;
Step S3:Double vision fusion treatment is carried out to the image of shooting with reference to image processing means, determines exception leak.
Step S4:Processing is amplified to abnormal leak, further determine that hot cloud figure dispersal direction, heat source position,
Size.
The step S3 includes:
(1)The visible images stored in visible ray realtime graphic and image sample data storehouse to shooting compare and analyze,
Precise positioning inspection position, finds out region to be detected;
(2)The visible images for corresponding to inspection point with image sample data storehouse to the visible ray realtime graphic of shooting carry out pixel
Point Linear contrasts, and analyses whether the abnormal phenomenon such as visible ray atomization cloud cluster occur;
(3)It will be seen that optical haze cloud cluster image compares infrared image, the profile of object in effective district split screen, by infrared gray-scale map
It is superimposed upon as merging in visible ray edge enhanced images, the infrared thermal diffusion image of Detection and Extraction abnormal motion.
Above-mentioned double vision convergence analysis algorithm includes:Visual image edge extracting;Infrared image and the linear RGB of visible images
Fusion;Image color space is changed.
Preferably, recognition methods proposed by the present invention further includes robot inspection point position according to residing for present, converses
Leak the physical location occurred.
The present invention also proposes a kind of high-temperature steam leakage automatic detecting identifying system, including:
Image sample data storehouse, for the visible ray for storing all inspection scene normal conditions and infrared double vision fusion figure;
Robot, for automatic detecting, is provided with an at least visible light camera and an at least thermal imaging system;
Judgment module is analyzed, for carrying out double vision convergence analysis processing to the realtime graphic of shooting, determines exception leak.
Preferably, the analysis judgment module is additionally operable to amplify abnormal leak image, further determines that hot cloud figure is spread
Direction and heat source position, size.
Compared with prior art, high-temperature steam leakage automatic detecting recognition methods proposed by the present invention and identifying system tool
There is following beneficial effect:
1. robot automatic detecting, when there is steam to leak extremely, machine can be passed through in complicated high-temperature steam operation environment
People can photograph the temperature change of abnormal leakage point, have the presentation of trend report, while have early warning and accident analysis.
2. can recognize that direction and the diffusion zone of steam leakage, authentic data is provided for subsequent treatment.
Brief description of the drawings
Fig. 1 is the structure diagram of identifying system of the present invention;
Fig. 2 is the flow chart of recognition methods of the present invention.
Embodiment
Since in high-temperature steam leak, steam leaks and can liquefy or even sublimate to the cold, and it is accompanied by exothermic phenomenon.This hair
Method that is bright to utilize this principle, being merged using visible ray and infrared thermal imaging double vision, the barber that visual camera is caught
Change the leak thermal diffusion dynamic area that the exact outline of cloud cluster and infrared thermal imagery are caught to be merged, improve environment heat distribution
Resolution ratio, and contrast the normal state that shoots in advance of the environment by analyzing and refer to double vision blending image, analyze and whether height occurs
Warm steam leakage, and can find accurate location and the leakage direction of leakage.
As shown in Figure 1, a kind of high-temperature steam leakage automatic detecting identifying system proposed by the present invention, including:
Image sample data storehouse, for the visible ray for storing all inspection scene normal conditions and infrared double vision fusion figure;
Robot, for automatic detecting, robot carries an at least visible light camera and an at least thermal imaging system;
Judgment module is analyzed, for carrying out double vision convergence analysis processing to the realtime graphic of shooting, determines exception leak, diffusion
Direction and heat source position, size.
High-temperature steam leakage automatic detecting recognition methods proposed by the present invention includes:
Step S1:Image sample data storehouse is established, for the visible ray for storing all inspection scene normal conditions and infrared double vision
Fusion figure;
Step S2:Using robot automatic detecting, robot carries visible light camera and thermal imaging system shoots the real-time of inspection point
Image;
Step S3:Double vision convergence analysis processing is carried out to the realtime graphic of shooting, determines exception leak;
Step S4:The abnormal leak image of amplification, according to heat transfer by high temperature to low temperature, the characteristics of by source of leaks to air, into
One step determines hot cloud figure dispersal direction and heat source position, size.
As shown in Fig. 2, in a particular embodiment, the method for the various occasion high-temperature steam leakages of automatic identification of the present invention is specific
Comprise the following steps:
Step 1:To the normal condition visible ray of all inspection scenes of system typing and infrared double vision fusion figure, as with reference to figure
As storehouse, judge to refer to for system subsequent contrast.
Step 2:Robot automatic detecting, to inspection point visible light camera and thermal imaging system shooting image.
The visible images of shooting and Infrared image are carried out convergence analysis, analysis method is as follows by step 3:
1st, inspection point is reached, can be precisely fixed according to the visible images comparative analysis in visible ray realtime graphic and reference image storehouse
Position inspection position, finds out region to be detected, excludes the interference that robot localization is brought;
2nd, in region to be detected, shooting realtime graphic f1 (x, y) inspection point picture f2 (x, y) pixels corresponding to reference picture library
Contrasted, analysed whether abnormal visible ray atomization cloud cluster image, as shown in formula 1
(1)
I in formula, j are respectively image ranks coordinate, and S is scaling coefficient, and M is decision threshold.
3rd, in region to be detected, it is seen that light is than infrared profile that can be in effective district split screen, therefore by infrared gray-scale map
It is superimposed upon as merging in visible ray edge enhanced images, the infrared thermal diffusion image section of Detection and Extraction abnormal motion, and according to
Heat transfer is by high temperature to low temperature, by the feature that flows to of source of leaks to air, extraction leakage direction and leakage position and size.
The Image Fusion specifically used is as follows:
Visual image edge extracting.
With the edge detection algorithm of Prewitt first order differential operators, visible images edge is obtained.Using on pixel
Under, the gray scale difference of left and right adjoint point, extremum extracting edge is reached in edge, removes part pseudo-edge, using medium filtering to making an uproar
Sound is smoothed.Edge detection carries out neighborhood convolution using horizontal, vertical direction template and image, to digital picture f
(x, y), Edge definition are as follows:
Horizontal edge:G (i)=| [f (i-1, j-1)+f (i-1, j)+f (i-1, j+1)]-[f (i+1, j-1)+f (i+1, j)+f (i+
1, j+1)] |
Vertical edge:G (j)=| [f (i-1, j+1)+f (i, j+1)+f (i+1, j+1)]-[f (i-1, j-1)+f (i, j-1)+f (i+
1, j-1)] |
Then edge P (i, j)=max [G (i), G (j)] or P (i, j)=G (i)+G (j)
Infrared image and the linear RGB fusion formulas equation below 2 of visible images, are relatively met and appoint the puppet of eye vision color
Color blending image:
(2)
Wherein, IirFor infrared image, IvisFor visual image;miRepresent fusion coefficients, mi >0, i=1,2,3,4, and meet m1
+m2=1, m3+m4=1.This mode fusion results make it that thermal radiation temperature takes on a red color gradient color, meets human-eye visual characteristic.Through
After fusion, the infrared and difference of visual image is as R channel values, visually with infrared difference as G channel values, i.e. infrared image
The pixel that middle gray value is more than gray value in visual image takes on a red color, otherwise in green.
Color transfer algorithm carries out color space conversion fusion coloring, improves accuracy of identification:
Infrared image pyramid construction:First using original image as bottom image G0, it is rolled up using 5x5 Gaussian kernels
Product, then carries out the image after convolution down-sampled(Remove even number row and column)Obtain last layer image G1, using this image as
Input, repeats convolution and down-sampling operates to obtain more last layer image, iterates repeatedly, forms a pyramidal image
Data structure, it is assumed that pyramidal L tomographic images are Gl.
N is gaussian pyramid top layer level number, and Rl and Cl are respectively the line number and columns of l layers of pyramid, w(M, n)It is one two
Separable 5x5 window functions are tieed up, expression formula is:
By G0, G1, GN, an image pyramid is just constituted.
Rendering operations are carried out using equation below to each layer of pyramid Gi, R, G, B are respectively R, G of Gi, channel B pixel
Value, X, Y, Z are to render rear image R, G, channel B pixel value.
Wherein:After the completion of pyramid image rendering, interpolated value method is successively used since its image top layer, can be obtained
Infrared image to after rendering.
Step 3:Such as find No leakage thermal map and vaporific cloud cluster, then the leakage without exception of inspection point region.
Step 4:Such as finding leakage cloud atlas, amplification leak further analyzes thermal map dispersal direction, heat source position etc., and
Robot inspection point absolute location coordinates according to residing for present are(X,Y,θ), wherein, X, Y are robot absolute location coordinates, θ
For robot pose angle.Heat source position is L relative to the approximate distance of robot positive direction, and direction is Ф.It can then calculate and let out
Leak heat source and point position occurs.
Proposed by the present invention is that can be instead of manpower automatic detecting in the place of environment complexity by system and recognition methods
It is no to there is high-temperature steam to leak extremely, human cost is saved, lifts automatization level.In addition, the present invention can also judge have
Leakage direction is judged in the case of leakage, the information such as source size, leak position is leaked, accurate foundation is provided for subsequent treatment.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of high-temperature steam leaks automatic detecting recognition methods, it is characterised in that including
Step S1:An image library is established, for the visible ray for storing all inspection scene normal conditions and infrared double vision fusion figure;
Step S2:Using robot automatic detecting, with visible light camera and the realtime graphic of thermal imaging system shooting inspection point;
Step S3:Double vision convergence analysis processing is carried out to the realtime graphic of shooting, determines exception leak.
2. recognition methods as claimed in claim 1, it is characterised in that further include step S4:The abnormal leak image of amplification, into
One step determines hot cloud figure dispersal direction and heat source position, size.
3. recognition methods as claimed in claim 1, it is characterised in that step S3 includes:
(1)According to the visible images comparative analysis stored in visible ray realtime graphic and image library, precise positioning inspection position,
Find out region to be detected;
(2)It is linear right that the visible images pixel of the visible ray realtime graphic of shooting inspection point corresponding with image library is carried out
Than having analysed whether abnormal visible ray atomization cloud cluster image;
(3)It will be seen that optical haze cloud cluster image compares infrared image, the profile in effective district split screen, infrared hybrid optical system is melted
Conjunction is superimposed upon in visible ray edge enhanced images, the infrared thermal diffusion image of Detection and Extraction abnormal motion.
4. such as claim 1-3 any one of them recognition methods, it is characterised in that the double vision convergence analysis algorithm includes:
Visual image edge extracting;Infrared image is merged with the linear RGB of visible images;It is empty with color is carried out using color transfer algorithm
Between conversion fusion coloring, improve accuracy of identification.
5. recognition methods as claimed in claim 4, it is characterised in that the visual image edge extracting includes:With
The edge detection algorithm of Prewitt first order differential operators, obtain seeing light image edge, using above and below pixel, left and right adjoint point
Gray scale difference, extremum extracting edge is reached in edge, removes part pseudo-edge, and smoothing processing is done to noise.
6. recognition methods as claimed in claim 4, it is characterised in that the linear RGB fusion methods are such as
Under:
Wherein, mi>0, i=1,2,3,4 represent fusion coefficients, and meet m1+m2=1, m3+m4=1.
7. identifying system as claimed in claim 4, it is characterised in that described to carry out color space turn using color transfer algorithm
Fusion coloring is changed, accuracy of identification is improved and is calculated as follows:
Wherein:。
8. identifying system as claimed in claim 1, it is characterised in that further include robot inspection point position according to residing for present
Put, converse the actual absolute position that leakage occurs.
9. a kind of high-temperature steam leaks automatic detecting identifying system, it is characterised in that including:
Image library, for the visible ray for storing all inspection scene normal conditions and infrared double vision fusion figure;
Robot, for automatic detecting, is provided with an at least visible light camera and an at least thermal imaging system;
Judgment module is analyzed, for carrying out double vision convergence analysis processing to the realtime graphic of shooting, determines exception leak.
10. identifying system as claimed in claim 1, it is characterised in that the analysis judgment module is additionally operable to amplification exception and lets out
Leak image, further determines that hot cloud figure dispersal direction and heat source position, size.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711423014.4A CN107992857A (en) | 2017-12-25 | 2017-12-25 | A kind of high-temperature steam leakage automatic detecting recognition methods and identifying system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711423014.4A CN107992857A (en) | 2017-12-25 | 2017-12-25 | A kind of high-temperature steam leakage automatic detecting recognition methods and identifying system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107992857A true CN107992857A (en) | 2018-05-04 |
Family
ID=62042491
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711423014.4A Pending CN107992857A (en) | 2017-12-25 | 2017-12-25 | A kind of high-temperature steam leakage automatic detecting recognition methods and identifying system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107992857A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108711252A (en) * | 2018-09-06 | 2018-10-26 | 青岛海大新星软件咨询有限公司 | A kind of home intelligent management system |
CN109488888A (en) * | 2018-11-06 | 2019-03-19 | 沈阳天眼智云信息科技有限公司 | Based on the metallic conduit leakage monitoring method to the multivariate analysis of infrared temperature field |
CN109780451A (en) * | 2018-12-20 | 2019-05-21 | 国电大渡河沙坪水电建设有限公司 | A kind of power plant's governor oil circuit method for inspecting based on machine vision |
CN109798449A (en) * | 2018-12-20 | 2019-05-24 | 国电大渡河沙坪水电建设有限公司 | Water system method for inspecting and system based on machine vision unit neural network |
CN109854964A (en) * | 2019-03-29 | 2019-06-07 | 沈阳天眼智云信息科技有限公司 | Steam leakage positioning system and method based on binocular vision |
CN109915736A (en) * | 2019-03-15 | 2019-06-21 | 山东建筑大学 | A kind of method of heat distribution pipe network system and its leak detection |
CN110173627A (en) * | 2019-06-03 | 2019-08-27 | 山东建筑大学 | A kind of solar energy system |
CN110274160A (en) * | 2019-06-13 | 2019-09-24 | 咏峰(大连)科技有限公司 | A kind of pipeline cruising inspection system based on infrared visible light blending image |
CN110513604A (en) * | 2019-09-09 | 2019-11-29 | 朱晓斌 | A kind of LNG station leakage intelligent checking system and its detection method based on multi-source image |
CN111047568A (en) * | 2019-12-06 | 2020-04-21 | 汕头大学 | Steam leakage defect detection and identification method and system |
CN111521279A (en) * | 2020-06-05 | 2020-08-11 | 中国有色金属长沙勘察设计研究院有限公司 | Pipeline leakage inspection method |
CN113945326A (en) * | 2021-12-21 | 2022-01-18 | 广州市腾嘉自动化仪表有限公司 | Hyperspectral infrared gas leakage detection system and method |
CN113945570A (en) * | 2021-10-12 | 2022-01-18 | 揭阳市大立模具厂有限公司 | Detection and identification method for micro-leakage steam defects based on steam characteristic infrared characterization |
CN114112214A (en) * | 2021-12-13 | 2022-03-01 | 广州市腾嘉自动化仪表有限公司 | Infrared imaging system for detecting gas leakage |
CN114274143A (en) * | 2021-12-28 | 2022-04-05 | 华能汕头海门发电有限责任公司 | Intelligent identification method for centralized control operation defect image of intelligent robot group in thermal power plant |
WO2022101628A1 (en) * | 2020-11-12 | 2022-05-19 | Synovate Limited | Leak detection |
CN115452060A (en) * | 2022-10-26 | 2022-12-09 | 数字太空(北京)科技股份公司 | Non-contact full-time detection system and method for chemical storage and transportation area |
CN116659764A (en) * | 2023-07-26 | 2023-08-29 | 山东省阳信根深电气有限公司 | Device and method for tightness test of distribution box |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5742053A (en) * | 1996-11-29 | 1998-04-21 | Rekunyk; Horace | Infrared gas detection method and apparatus |
CN102547063A (en) * | 2012-02-08 | 2012-07-04 | 南京航空航天大学 | Natural sense color fusion method based on color contrast enhancement |
CN103775830A (en) * | 2014-01-20 | 2014-05-07 | 武汉第二船舶设计研究所 | High-temperature stream leakage detection positioning system and high-temperature stream leakage detection positioning method |
CN104075121A (en) * | 2014-06-04 | 2014-10-01 | 国家电网公司 | Pipeline steam leakage monitoring device adopting infrared spectrums |
CN104977129A (en) * | 2014-04-10 | 2015-10-14 | 通用电气公司 | Method And System For Detecting Leaks In Steam Turbines |
CN105203465A (en) * | 2015-09-16 | 2015-12-30 | 湖北久之洋红外系统股份有限公司 | Hyperspectral infrared imaging gas monitoring device and monitoring method thereof |
CN105486459A (en) * | 2016-01-23 | 2016-04-13 | 国家电网公司 | Transformer substation gas leakage detection mobile platform and detection method |
-
2017
- 2017-12-25 CN CN201711423014.4A patent/CN107992857A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5742053A (en) * | 1996-11-29 | 1998-04-21 | Rekunyk; Horace | Infrared gas detection method and apparatus |
CN102547063A (en) * | 2012-02-08 | 2012-07-04 | 南京航空航天大学 | Natural sense color fusion method based on color contrast enhancement |
CN103775830A (en) * | 2014-01-20 | 2014-05-07 | 武汉第二船舶设计研究所 | High-temperature stream leakage detection positioning system and high-temperature stream leakage detection positioning method |
CN104977129A (en) * | 2014-04-10 | 2015-10-14 | 通用电气公司 | Method And System For Detecting Leaks In Steam Turbines |
CN104075121A (en) * | 2014-06-04 | 2014-10-01 | 国家电网公司 | Pipeline steam leakage monitoring device adopting infrared spectrums |
CN105203465A (en) * | 2015-09-16 | 2015-12-30 | 湖北久之洋红外系统股份有限公司 | Hyperspectral infrared imaging gas monitoring device and monitoring method thereof |
CN105486459A (en) * | 2016-01-23 | 2016-04-13 | 国家电网公司 | Transformer substation gas leakage detection mobile platform and detection method |
Non-Patent Citations (4)
Title |
---|
DANGDANG D.等: "Leakage Region Detection of Gas Insulated Equipment by Applying Infrared Image Processing Technique", 《2017 9TH INTERNATIONAL CONFERENCE ON MEASURING TECHNOLOGY AND MECHATRONICS AUTOMATION (ICMTMA)》 * |
孔韦韦 等: "《图像融合技术—基于多分辨率非下采样理论与方法》", 31 July 2015, 西安:西安电子科技大学出版社 * |
张文峦: "基于伪彩色的图像融合算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
高宏伟: "《电子封装工艺与装备技术基础教程》", 31 July 2017, 西安:电子科技大学出版社 * |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108711252A (en) * | 2018-09-06 | 2018-10-26 | 青岛海大新星软件咨询有限公司 | A kind of home intelligent management system |
CN109488888A (en) * | 2018-11-06 | 2019-03-19 | 沈阳天眼智云信息科技有限公司 | Based on the metallic conduit leakage monitoring method to the multivariate analysis of infrared temperature field |
CN109488888B (en) * | 2018-11-06 | 2020-07-17 | 沈阳天眼智云信息科技有限公司 | Metal pipeline leakage monitoring method based on infrared temperature field multivariate analysis |
CN109780451B (en) * | 2018-12-20 | 2021-01-05 | 国电大渡河沙坪水电建设有限公司 | Power plant speed regulator oil circuit inspection method based on machine vision |
CN109780451A (en) * | 2018-12-20 | 2019-05-21 | 国电大渡河沙坪水电建设有限公司 | A kind of power plant's governor oil circuit method for inspecting based on machine vision |
CN109798449A (en) * | 2018-12-20 | 2019-05-24 | 国电大渡河沙坪水电建设有限公司 | Water system method for inspecting and system based on machine vision unit neural network |
CN109798449B (en) * | 2018-12-20 | 2021-08-10 | 国能大渡河沙坪发电有限公司 | Water supply system inspection method and system based on machine vision unit neural network |
CN109915736A (en) * | 2019-03-15 | 2019-06-21 | 山东建筑大学 | A kind of method of heat distribution pipe network system and its leak detection |
CN109915736B (en) * | 2019-03-15 | 2020-07-17 | 山东建筑大学 | Thermal pipe network system and leakage detection method thereof |
CN109854964A (en) * | 2019-03-29 | 2019-06-07 | 沈阳天眼智云信息科技有限公司 | Steam leakage positioning system and method based on binocular vision |
CN109854964B (en) * | 2019-03-29 | 2021-03-19 | 沈阳天眼智云信息科技有限公司 | Steam leakage positioning system and method based on binocular vision |
CN110173627A (en) * | 2019-06-03 | 2019-08-27 | 山东建筑大学 | A kind of solar energy system |
CN110274160A (en) * | 2019-06-13 | 2019-09-24 | 咏峰(大连)科技有限公司 | A kind of pipeline cruising inspection system based on infrared visible light blending image |
CN110274160B (en) * | 2019-06-13 | 2021-05-11 | 咏峰(大连)科技有限公司 | Pipeline inspection system based on infrared and visible light fusion image |
CN110513604A (en) * | 2019-09-09 | 2019-11-29 | 朱晓斌 | A kind of LNG station leakage intelligent checking system and its detection method based on multi-source image |
CN111047568A (en) * | 2019-12-06 | 2020-04-21 | 汕头大学 | Steam leakage defect detection and identification method and system |
CN111047568B (en) * | 2019-12-06 | 2023-05-16 | 汕头大学 | Method and system for detecting and identifying steam leakage defect |
CN111521279B (en) * | 2020-06-05 | 2021-06-25 | 中国有色金属长沙勘察设计研究院有限公司 | Pipeline leakage inspection method |
CN111521279A (en) * | 2020-06-05 | 2020-08-11 | 中国有色金属长沙勘察设计研究院有限公司 | Pipeline leakage inspection method |
WO2022101628A1 (en) * | 2020-11-12 | 2022-05-19 | Synovate Limited | Leak detection |
GB2604210A (en) * | 2020-11-12 | 2022-08-31 | Synovate Ltd | Leak detection |
CN113945570A (en) * | 2021-10-12 | 2022-01-18 | 揭阳市大立模具厂有限公司 | Detection and identification method for micro-leakage steam defects based on steam characteristic infrared characterization |
CN114112214A (en) * | 2021-12-13 | 2022-03-01 | 广州市腾嘉自动化仪表有限公司 | Infrared imaging system for detecting gas leakage |
CN113945326B (en) * | 2021-12-21 | 2022-03-22 | 广州市腾嘉自动化仪表有限公司 | Hyperspectral infrared gas leakage detection system and method |
CN113945326A (en) * | 2021-12-21 | 2022-01-18 | 广州市腾嘉自动化仪表有限公司 | Hyperspectral infrared gas leakage detection system and method |
CN114274143A (en) * | 2021-12-28 | 2022-04-05 | 华能汕头海门发电有限责任公司 | Intelligent identification method for centralized control operation defect image of intelligent robot group in thermal power plant |
CN115452060A (en) * | 2022-10-26 | 2022-12-09 | 数字太空(北京)科技股份公司 | Non-contact full-time detection system and method for chemical storage and transportation area |
CN116659764A (en) * | 2023-07-26 | 2023-08-29 | 山东省阳信根深电气有限公司 | Device and method for tightness test of distribution box |
CN116659764B (en) * | 2023-07-26 | 2023-10-20 | 山东省阳信根深电气有限公司 | Device and method for tightness test of distribution box |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107992857A (en) | A kind of high-temperature steam leakage automatic detecting recognition methods and identifying system | |
CN102830793B (en) | Sight tracing and equipment | |
CN108171673B (en) | Image processing method and device, vehicle-mounted head-up display system and vehicle | |
EP3073894B1 (en) | Corrected 3d imaging | |
CN111047568B (en) | Method and system for detecting and identifying steam leakage defect | |
CN106851238A (en) | Method for controlling white balance, white balance control device and electronic installation | |
CN109754377A (en) | A kind of more exposure image fusion methods | |
Wu et al. | Passive measurement method of tree diameter at breast height using a smartphone | |
US10310619B2 (en) | User gesture recognition | |
CN112508903B (en) | Method for detecting surface defect contour of lens of satellite telescope | |
CN107203743B (en) | Face depth tracking device and implementation method | |
KR102528507B1 (en) | Hybrid thermal image based object detection method combining YOLO model and object tracking technique | |
CN112712059A (en) | Living body face recognition method based on infrared thermal image and RGB image | |
CN105678737B (en) | A kind of digital picture angular-point detection method based on Radon transformation | |
Lee et al. | Kinect who's coming—applying Kinect to human body height measurement to improve character recognition performance | |
Chen et al. | 3D reconstruction from IR thermal images and reprojective evaluations | |
CN105913464A (en) | Multi-body target online measurement method based on videos | |
CN103761011B (en) | A kind of method of virtual touch screen, system and the equipment of calculating | |
JP4818285B2 (en) | Congestion retention detection system | |
CN105139432B (en) | Infrared DIM-small Target Image emulation mode based on Gauss model | |
CN104239845B (en) | The identification of double vision intelligent image and object localization method based on infrared thermal imaging technique | |
CN115100556B (en) | Augmented reality method and device based on image segmentation and fusion and electronic equipment | |
US20230091536A1 (en) | Camera Placement Guidance | |
JP4082718B2 (en) | Image recognition method, image display method, and image recognition apparatus | |
CN113688849B (en) | Gray image sequence feature extraction method for convolutional neural network |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180504 |