CN103163181B - Automatic thermotechnical area identification method based on outdoor scene infrared image of building - Google Patents
Automatic thermotechnical area identification method based on outdoor scene infrared image of building Download PDFInfo
- Publication number
- CN103163181B CN103163181B CN201310091937.XA CN201310091937A CN103163181B CN 103163181 B CN103163181 B CN 103163181B CN 201310091937 A CN201310091937 A CN 201310091937A CN 103163181 B CN103163181 B CN 103163181B
- Authority
- CN
- China
- Prior art keywords
- infrared image
- temperature
- main body
- area
- thermal
- 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.)
- Expired - Fee Related
Links
Landscapes
- Radiation Pyrometers (AREA)
Abstract
The invention relates to an automatic thermotechnical area identification method based on an outdoor scene infrared image of a building. The method comprises the steps of a, acquiring an infrared image; b, obtaining a whole panoramic infrared image; c, setting a detecting main body; d, establishing a histogram by taking temperature as the horizontal axis and temperature appearing frequency or pixel count as the vertical axis; e, acquiring the peak value temperature Tf; f, obtaining temperature thresholds Twi, Td and Tw2 of all thermotechnical areas of windows and defected and qualified walls; g, classifying the detecting main body; h, calculating the area of each thermotechnical area; and i, calculating thermotechnical detect rate, and giving primary analysis of conclusion. The automatic thermotechnical area identification method can effectively mark and obtain the thermotechnical areas of the windows and the defected and qualified walls of the detecting main body, and the primary thermotechnical defect analysis of conclusion can be given through calculating the thermotechnical defect rate. The identification effect is visualized and discremible, the method is flexible, simple and convenient to operate, the detection result can be stored, and the method can be widely applied to detection of large buildings.
Description
Technical field
The present invention relates to a kind of thermal areas automatic identifying method based on building outdoor scene infrared image, in particular, relate in particular to a kind of model histogram, ask for again the thermal areas automatic identifying method of the temperature threshold of window, defect and body of wall.
Background technology
Any temperature all can discharge infrared ray higher than the object of absolute zero, and its energy is directly proportional to the biquadratic of this object temperature.The infrared energy that thermal infrared imager can cannot be seen human eye is converted to electric signal, and represents that with the different color that makes preparations for sowing the visual image that different temperatures distributes shows.These visual data-signals can assist people to search temperature anomaly point, thereby before fault does not occur, find potential faults, the potential problems of identification equipment or system.
From twentieth century, since the seventies, more American-European developed countries have successively started the exploration that thermal infrared imager is safeguarded in the diagnosis of structural engineering field, and Infrared Thermography Technology is become better and approaching perfection day by day in the application in this field.Domestic infrared building detects in nineteen nineties and starts starting, mainly concentrates at the beginning bond quality and the leak detection aspect of exposed wall facing brick.Because these applications do not have other applicable detection means, and having large area, noncontact, infrared thermal imaging technique detects at a distance, do not affect testee, use safety, the advantages such as detection is quick, and visual result is visual, make this technology obtain swift and violent development at building field.Use thermal infrared imager, the architectural feature of air leakage, moisture accumulation, line clogging, behind walls and overheated electric wiring etc. can be detected, and data are carried out to visual record filing.
The main application that thermal infrared imager detects in building at present has:
(1) detection of construction energy conservation: detect thermal defects, heat bridge defect, outer wall heat insulating energy savings etc., guarantee building performance and quality, avoid causing heavy losses or harm, and building energy conservation is played to assessment effect.
(2) construction quality detects: for detections such as leakage of building, electrical system, heating ventilation air-conditioning system, pipe systems, and, electric fault bad such as: infiltration, sloughing of exterior wall, seal for pipe joints etc.
Due to environmental protection and energy-conservation in the urgent need to, both at home and abroad particularly the developed country such as Canada, the U.S., Japan to infrared thermal imaging in energy-conservation applied research, obtained rich experience and achievement.
Infrared thermal imaging detection technique is a kind of effective detection means of successfully having used building energy conservation and the defect of more than 30 year.For the pre-maintenance of all aspects of large Minor Construction, infrared detection is a kind of mode that effectively reduces the most energy consumption and maintenance cost.Along with scientific and technical development, along with our transformation to the further understanding of Infrared Thermography Technology and scientific research thinking and theory, Infrared Thermography Technology will reach its maturity, and its research at building field will have more wide prospect with application.
Summary of the invention
The present invention, in order to overcome the shortcoming of above-mentioned technical matters, provides a kind of thermal areas automatic identifying method based on building outdoor scene infrared image.
Thermal areas automatic identifying method based on building outdoor scene infrared image of the present invention, its special feature is, comprise the following steps: a). gather infrared image, indoor higher than the condition of outdoor 10 ℃ under, utilize thermal infrared imager to carry out location shooting to buildings to be detected, to obtain original infrared picture data; B). obtain full outdoor scene infrared image, original infrared image is carried out to panorama splicing, to obtain the full outdoor scene infrared image that buildings to be detected is complete; For the aedicula that only has an infrared image, omit this step; C). set and detect main body, in full outdoor scene infrared image, uncorrelated background and chaff interference are foreclosed, set out by hand the detection main body of buildings to be detected; D). set up to detect the histogram distribution of main body, the temperature of the detection main body of take in infrared image to be characterized is that frequency or the pixel count that transverse axis, each temperature occur is the longitudinal axis, sets up histogram distribution; E). obtain peak temperature
, establish
for histogrammic peak temperature, be defined as the frequency of occurrences or the maximum temperature value of pixel count in histogram; F). ask for the temperature threshold of each thermal areas, definition
,
with
be respectively the temperature threshold of window in infrared image, defect and qualified body of wall thermal areas;
When in detecting main body, the area of body of wall is greater than the area of window, histogram peak temperature
approach with qualified body of wall temperature,
,
with
temperature threshold is defined as follows:
When in detecting main body, the area of body of wall is less than the area of window, histogram peak temperature
approach with window temperature,
,
with
temperature threshold is defined as follows:
Wherein,
,
be respectively minimum, the maximum temperature value that detect in main body;
,
choose based on experience value,
>
;
G). will detect main body classification, by main body to be detected according to step f) in threshold range carry out region identification and divide, and in infrared image the position of mark exit window family, defect and qualified body of wall thermal areas; H). calculate the area of all kinds of thermal areas, calculate window, defect and qualified body of wall thermal areas area separately; G). calculate thermal defects ratio, according to: thermal defects ratio=(defect area area)/(detecting main body area-window areas), calculate the thermal defects ratio that detects main body, and thermal defects is compared than with GB parameter, provide preliminary thermal defects and analyze conclusion.
Step c) in, the uncorrelated backgrounds such as sky, trees and chaff interference should be foreclosed, to avoid it to affect testing result.Step f) in, defect thermal areas refers to the defect area of body of wall, and qualified body of wall thermal areas refers to the wall part that does not have defect, and the area of body of wall should be the area sum of defect area and qualified wall body area.
Thermal areas automatic identifying method based on building outdoor scene infrared image of the present invention, step f) in
,
value meet: 1≤
< 2; 2≤
< 4.
,
all obtain based on experience value.
Thermal areas automatic identifying method based on building outdoor scene infrared image of the present invention, step g) identification of region described in is divided and is adopted growth method, and it comprises the following steps: g-1). take that to detect the point that meets window, defect or a certain temperature threshold of qualified body of wall in the infrared image of main body be the starting point of growth; G-2). obtaining step g-1) in the temperature value of 8 neighborhood territory pixels of starting point periphery, and judge that in 8 neighborhood temperature values, those belong in the temperature threshold of current region; G-3). step g-2) in, if the temperature value of neighborhood point and current starting point belong to the same area, with this, put as new starting point, proceed the judgement of 8 pixel temperatures values in its neighborhood, the like; Until the pixel and the starting point that do not satisfy condition in 8 neighborhood temperature values belong to the same area again, stop search; G-4). step g-2) and g-3) in, if the temperature value of 8 pixels in neighborhood and starting point do not belong to the same area, this temperature value position, field stops search.
The invention has the beneficial effects as follows: the thermal areas automatic identifying method based on building outdoor scene infrared image of the present invention, first the temperature of take is set up histogram as transverse axis, frequency or pixel as the longitudinal axis, based on experience value, provide again the temperature threshold scope of window under different condition, defect and qualified body of wall thermal areas, can effectively demarcate and obtain the area of the window, defect and the qualified wall thermal areas that detect main body; By calculating thermal defects ratio, can provide preliminary thermal defects and analyze conclusion.Thermal areas automatic identifying method of the present invention, the infrared thermal-image data in winter that gathers building outdoor scene is analytic target, utilize the method can select adaptively the classification thresholds of thermal areas identification, simultaneously threshold value can manual setting, recognition effect intuitively can distinguish, method flexible operation is easy, and testing result can be stored, and can repeatedly analyze, can be widely used in building and detect.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of thermal areas automatic identifying method of the present invention;
Fig. 2 is the identification process figure of window in the present invention, defect and qualified body of wall thermal areas;
Fig. 3 adopts region-growing method to carry out the schematic diagram that region identification is divided in the present invention.
Embodiment
Below in conjunction with accompanying drawing and embodiment, the invention will be further described.
As depicted in figs. 1 and 2, provided the process flow diagram of thermal areas automatic identifying method of the present invention, the thermal areas automatic identifying method based on building outdoor scene infrared image that shown the present invention relates to comprises the following steps:
A). gather infrared image, indoor higher than the condition of outdoor 10 ℃ under, utilize thermal infrared imager to carry out location shooting to buildings to be detected, to obtain original infrared picture data;
B). obtain full outdoor scene infrared image, original infrared image is carried out to panorama splicing, to obtain the full outdoor scene infrared image that buildings to be detected is complete; For the aedicula that only has an infrared image, omit this step;
C). set and detect main body, in full outdoor scene infrared image, uncorrelated background and chaff interference are foreclosed, set out by hand the detection main body of buildings to be detected; Such as sky, trees etc., all should get rid of;
D). set up to detect the histogram distribution of main body, the temperature of the detection main body of take in infrared image to be characterized is that frequency or the pixel count that transverse axis, each temperature occur is the longitudinal axis, sets up histogram distribution;
E). obtain peak temperature
, establish
for histogrammic peak temperature, be defined as the frequency of occurrences or the maximum temperature value of pixel count in histogram;
F). ask for the temperature threshold of each thermal areas, definition
,
with
be respectively the temperature threshold of window in infrared image, defect and qualified body of wall thermal areas; Defect thermal areas refers to the defect part of wall body area, and qualified body of wall refers to the non-defect part of wall body area;
When in detecting main body, the area of body of wall is greater than the area of window, histogram peak temperature
approach with qualified body of wall temperature,
,
with
temperature threshold is defined as follows:
When in detecting main body, the area of body of wall is less than the area of window, histogram peak temperature
approach with window temperature,
,
with
temperature threshold is defined as follows:
Wherein,
,
be respectively minimum, the maximum temperature value that detect in main body;
,
choose based on experience value,
>
; Based on experience value,
,
desirable: 1≤
< 2; 2≤
< 4;
G). will detect main body classification, by main body to be detected according to step f) in threshold range carry out region identification and divide, and in infrared image the position of mark exit window family, defect and qualified body of wall thermal areas;
In this step, region identification is divided and can be adopted growth method, and as shown in Figure 3, it comprises the following steps:
G-1). take that to detect the point that meets window, defect or a certain temperature threshold of qualified body of wall in the infrared image of main body be the starting point of growth;
G-2). obtaining step g-1) in the temperature value of 8 neighborhood territory pixels of starting point periphery, and judge that in 8 neighborhood temperature values, those belong in the temperature threshold of current region;
G-3). step g-2) in, if the temperature value of neighborhood point and current starting point belong to the same area, with this, put as new starting point, proceed the judgement of 8 pixel temperatures values in its neighborhood, the like; Until the pixel and the starting point that do not satisfy condition in 8 neighborhood temperature values belong to the same area again, stop search;
G-4). step g-2) and g-3) in, if the temperature value of 8 pixels in neighborhood and starting point do not belong to the same area, this neighborhood position stops search.
H). calculate the area of all kinds of thermal areas, calculate window, defect and qualified body of wall thermal areas area separately;
G). calculate thermal defects ratio, according to: thermal defects ratio=(defect area area)/(detecting main body area-window areas), calculate the thermal defects ratio that detects main body, and thermal defects is compared than with GB parameter, provide preliminary thermal defects and analyze conclusion; If meet index, show building energy conservation, if the index of not meeting shows that building is not energy-conservation.
Claims (3)
1. the thermal areas automatic identifying method based on building outdoor scene infrared image, is characterized in that, comprises the following steps:
A). gather infrared image, under the condition in indoor temperature higher than 10 ℃ of outdoor temperatures, utilize thermal infrared imager to carry out location shooting to buildings to be detected, to obtain original infrared picture data;
B). obtain full outdoor scene infrared image, original infrared image is carried out to panorama splicing, to obtain the full outdoor scene infrared image that buildings to be detected is complete; For the aedicula that only has an infrared image, omit this step;
C). set and detect main body, in full outdoor scene infrared image, uncorrelated background and chaff interference are foreclosed, set out by hand the detection main body of buildings to be detected;
D). set up to detect the histogram distribution of main body, the temperature of the detection main body of take in infrared image to be characterized is that frequency or the pixel count that transverse axis, each temperature occur is the longitudinal axis, sets up histogram distribution;
E). obtain peak temperature
, establish
for histogrammic peak temperature, be defined as the frequency of occurrences or the maximum temperature value of pixel count in histogram;
F). ask for the temperature threshold of each thermal areas, definition
,
with
be respectively the temperature threshold of window in infrared image, defect and qualified body of wall thermal areas;
When in detecting main body, the area of body of wall is greater than the area of window, histogram peak temperature
approach with qualified body of wall temperature,
,
with
temperature threshold is defined as follows:
When in detecting main body, the area of body of wall is less than the area of window, histogram peak temperature
approach with window temperature,
,
with
temperature threshold is defined as follows:
Wherein,
,
be respectively minimum, the maximum temperature value that detect in main body;
,
choose based on experience value,
>
;
G). will detect main body classification, will detect main body according to step f) in threshold range carry out region identification division, and in infrared image the position of mark exit window family, defect and qualified body of wall thermal areas;
H). calculate the area of all kinds of thermal areas, calculate window, defect and qualified body of wall thermal areas area separately;
I). calculate thermal defects ratio, according to: thermal defects ratio=(defect area area)/(detecting main body area-window areas), calculate the thermal defects ratio that detects main body, and thermal defects is compared than with GB parameter, provide preliminary thermal defects and analyze conclusion.
2. the thermal areas automatic identifying method based on building outdoor scene infrared image according to claim 1, is characterized in that: step f)
,
value meet: 1≤
< 2; 2≤
< 4.
3. the thermal areas automatic identifying method based on building outdoor scene infrared image according to claim 1 and 2, is characterized in that: the region identification step g) is divided and adopted growth method, and it comprises the following steps:
G-1). take that to detect the point that meets window, defect or a certain temperature threshold of qualified body of wall in the infrared image of main body be the starting point of growth;
G-2). obtaining step g-1) in the temperature value of 8 neighborhood territory pixels of starting point periphery, and judge that in 8 neighborhood temperature values, which belongs in the temperature threshold of current region;
G-3). step g-2) in, if the temperature value of neighborhood point and current starting point belong to the same area, with this, put as new starting point, proceed the judgement of 8 pixel temperatures values in its neighborhood, the like; Until the pixel and the starting point that do not satisfy condition in 8 neighborhood temperature values belong to the same area again, stop search;
G-4). step g-2) and g-3) in, if the temperature value of 8 pixels in neighborhood and starting point do not belong to the same area, this neighborhood position stops search.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310091937.XA CN103163181B (en) | 2013-03-21 | 2013-03-21 | Automatic thermotechnical area identification method based on outdoor scene infrared image of building |
PCT/CN2013/000983 WO2014146222A1 (en) | 2013-03-21 | 2013-08-22 | Automatic detection method of building thermotechnical indicator based on infrared images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310091937.XA CN103163181B (en) | 2013-03-21 | 2013-03-21 | Automatic thermotechnical area identification method based on outdoor scene infrared image of building |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103163181A CN103163181A (en) | 2013-06-19 |
CN103163181B true CN103163181B (en) | 2014-11-05 |
Family
ID=48586443
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310091937.XA Expired - Fee Related CN103163181B (en) | 2013-03-21 | 2013-03-21 | Automatic thermotechnical area identification method based on outdoor scene infrared image of building |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103163181B (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105352988B (en) * | 2015-10-23 | 2018-03-27 | 吉林省智星红外科技有限公司 | A kind of skin heat-insulating property assessment system and method |
CN105352963A (en) * | 2015-12-07 | 2016-02-24 | 福州大学 | Device for distinguishing stability of building external wall member and use method of device |
CN107271044B (en) * | 2017-05-03 | 2020-10-23 | 北京海顿中科技术有限公司 | Thermal imaging temperature monitoring device and method |
CN109523544B (en) * | 2018-11-26 | 2021-02-26 | 陕西汉通建设工程质量检测有限公司 | Building outer wall quality defect detection system and method thereof |
CN110956196B (en) * | 2019-10-11 | 2024-03-08 | 东南大学 | Automatic recognition method for window wall ratio of urban building |
CN112964370B (en) * | 2021-03-30 | 2022-03-29 | 清华大学 | Method for rapidly acquiring indoor air temperature from outdoor in batch through infrared thermal imaging |
CN114676861B (en) * | 2022-05-27 | 2022-08-02 | 石家庄星海高科非金属矿业材料有限责任公司 | Energy-saving and environment-friendly maintenance method and system for outer vertical surface of building |
CN115598178B (en) * | 2022-12-14 | 2023-05-05 | 天津思睿信息技术有限公司 | Infrared detection method and system for building wall hollowing defect |
CN117689660A (en) * | 2024-02-02 | 2024-03-12 | 杭州百子尖科技股份有限公司 | Vacuum cup temperature quality inspection method based on machine vision |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS62172249A (en) * | 1986-01-25 | 1987-07-29 | Kajima Corp | Method and apparatus for diagnosing deterioration of chimney |
JP2892896B2 (en) * | 1993-02-04 | 1999-05-17 | 三菱電機ビルテクノサービス株式会社 | Wall peeling judgment device |
WO2003062809A1 (en) * | 2002-01-23 | 2003-07-31 | Marena Systems Corporation | Infrared thermography for defect detection and analysis |
JP5318728B2 (en) * | 2009-11-04 | 2013-10-16 | 大和小田急建設株式会社 | Deformation detection method of concrete surface layer by infrared method |
CN101806762A (en) * | 2010-05-31 | 2010-08-18 | 哈尔滨工业大学 | Method for identifying thermal defects by means of auxiliary heat source under condition of small temperature difference |
JP5017507B1 (en) * | 2011-04-08 | 2012-09-05 | 株式会社古田設計 | Image processing method, image processing apparatus, building image diagnosis method, and building image diagnosis apparatus |
-
2013
- 2013-03-21 CN CN201310091937.XA patent/CN103163181B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN103163181A (en) | 2013-06-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103163181B (en) | Automatic thermotechnical area identification method based on outdoor scene infrared image of building | |
CN103196565B (en) | The energy-conservation check point labeling method of architecture indoor based on infrared chart | |
CN103196380B (en) | Transmission line of electricity image collecting device and electric power line ice-covering thickness detection system | |
CN103234465B (en) | A kind of electric power line ice-covering thickness detection method and system | |
CN105574855B (en) | Infrared small target detection method under cloud background based on template convolution and false alarm rejection | |
CN103077504B (en) | A kind of image defogging method capable based on self-adaptation illumination calculation | |
WO2014146222A1 (en) | Automatic detection method of building thermotechnical indicator based on infrared images | |
CN103487729A (en) | Electrical equipment defect detection method based on fusion of ultraviolet video and infrared video | |
CN103063166B (en) | Detection method and device for wind deflection angle of suspension type composite insulator chain | |
CN105574468A (en) | Video flame detection method, device and system | |
CN112365669A (en) | Dual-band far infrared fusion-superposition imaging and fire early warning method and system | |
CN103679704A (en) | Video motion shadow detecting method based on lighting compensation | |
CN108334824B (en) | High-voltage isolating switch state identification method based on background difference and iterative search | |
CN106525859A (en) | Method for detecting strand breakage defect of high-voltage electric transmission wire by unmanned aerial vehicle in real time | |
CN102346014A (en) | Method for measuring arc sag of wire of power transmission line based on image processing | |
CN107169966B (en) | Power transmission line forest fire identification method based on temperature distribution | |
Zhong et al. | Pipeline leakage detection for district heating systems using multisource data in mid-and high-latitude regions | |
CN104573713A (en) | Mutual inductor infrared image recognition method based on image textual features | |
CN105678213A (en) | Dual-mode masked man event automatic detection method based on video characteristic statistics | |
CN112001327A (en) | Valve hall equipment fault identification method and system | |
CN105303158A (en) | Line-fitting video intelligent analysis algorithm for disconnecting switch of transformer station | |
CN105096305A (en) | Method and device for analyzing state of insulators | |
CN109580109A (en) | A kind of method that soft straight converter valve tower cooler water leak monitors automatically | |
CN103729620A (en) | Multi-view pedestrian detection method based on multi-view Bayesian network | |
CN110378866B (en) | Channel lining damage image identification method based on unmanned aerial vehicle inspection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141105 Termination date: 20150321 |
|
EXPY | Termination of patent right or utility model |