CN114387253A - Infrared image processing method and device for defects of external thermal insulation layer of external wall and storage medium - Google Patents

Infrared image processing method and device for defects of external thermal insulation layer of external wall and storage medium Download PDF

Info

Publication number
CN114387253A
CN114387253A CN202210033970.6A CN202210033970A CN114387253A CN 114387253 A CN114387253 A CN 114387253A CN 202210033970 A CN202210033970 A CN 202210033970A CN 114387253 A CN114387253 A CN 114387253A
Authority
CN
China
Prior art keywords
infrared image
defect
insulation layer
external
defects
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
CN202210033970.6A
Other languages
Chinese (zh)
Inventor
段中兴
焦晨琳
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.)
Xian University of Architecture and Technology
Original Assignee
Xian University of Architecture and Technology
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 Xian University of Architecture and Technology filed Critical Xian University of Architecture and Technology
Priority to CN202210033970.6A priority Critical patent/CN114387253A/en
Publication of CN114387253A publication Critical patent/CN114387253A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/143—Segmentation; Edge detection involving probabilistic approaches, e.g. Markov random field [MRF] modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10048—Infrared image

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Investigating Or Analyzing Materials Using Thermal Means (AREA)
  • Radiation Pyrometers (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses an infrared image processing method, a device and a storage medium for defects of an external thermal insulation layer of an external wall, wherein the infrared image processing method comprises the following steps: acquiring an infrared image of the defect of the external insulation layer to be treated; and inputting the infrared image of the defect of the outer insulating layer to be processed into a pre-constructed region growing infrared image segmentation processing model improved based on a two-dimensional OTSU threshold method, and outputting the defect image after the segmentation of the outer insulating layer of the outer wall. The method can conveniently, rapidly and accurately acquire the defect image of the external insulation layer of the building external wall, and the acquired fuzzy defect image can be intuitively and clearly displayed after being processed.

Description

Infrared image processing method and device for defects of external thermal insulation layer of external wall and storage medium
Technical Field
The invention belongs to the technical field of acquisition and processing of external wall external insulation layer defect images, and particularly relates to an external wall external insulation layer defect infrared image processing method and device and a storage medium.
Background
How to bring the energy-saving work of buildings into the whole construction management has become one of the most important problems of the new-era construction. In the future development, the research on the external thermal insulation system of the external wall is a key point of the energy-saving work of the building, wherein the detection and treatment research on the defects of the external thermal insulation layer should draw attention of people.
At present, the defect detection and identification of the external insulation layer of the external wall is in the starting stage of research, the defect problem which is easy to appear on the external insulation layer of the external wall of the existing building is lack of normative detection and image processing technology, and the reason and the development trend of the problem can not be scientifically and accurately judged. The traditional detection methods adopted at present comprise a visual detection method, a tapping method and a drawing method, which need manual participation, have great limitations, poor flexibility, great subjective factor influence and easy damage to samples. In order to clearly show the form of the defect, the detected infrared defect image needs to be segmented, and the following two difficulties mainly exist in the process: firstly, the infrared image is greatly influenced by noise due to the performance of the thermal infrared imager, environmental interference and the like, and error segmentation is easily caused; secondly, due to the thermal diffusion effect, the gray value between the defect area and the non-defect area changes smoothly, and the defect edge is difficult to detect accurately. The existing segmentation method such as infrared image segmentation processing based on filtering and phase stretching transformation can remove background, inhibit noise and segment defect regions, but the infrared defect image of the external thermal insulation layer segmented by the method, particularly the hollow defect image, still has the condition of incomplete segmentation or excessive segmentation.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an infrared image processing method, device and storage medium for defects of an external thermal insulation layer of an external wall, which can conveniently, rapidly and accurately acquire the images of the defects of the external thermal insulation layer of the external wall of a building, and can visually and clearly display the acquired blurred images after processing.
In order to solve the technical problems, the invention is realized by the following technical scheme:
an infrared image processing method for defects of an external thermal insulation layer of an external wall comprises the following steps:
acquiring an infrared image of the defect of the external insulation layer to be treated;
and inputting the infrared image of the defect of the outer insulating layer to be processed into a pre-constructed region growing infrared image segmentation processing model improved based on a two-dimensional OTSU threshold method, and outputting the defect image after the segmentation of the outer insulating layer of the outer wall.
Further, the construction method of the two-dimensional OTSU thresholding-based improved region growing infrared image segmentation processing model comprises the following steps:
acquiring an external insulation layer defect infrared image, determining an optimal threshold value of the external insulation layer defect infrared image, and generating a gray scale image of the external insulation layer defect infrared image;
and constructing a sliding matrix to traverse the gray-scale map to select initial seed points of region growth, determining a growth criterion based on the optimal threshold value and updating the growth criterion to obtain the improved region growth infrared image segmentation processing model based on the two-dimensional OTSU threshold value method.
Further, the determining an optimal threshold value of the infrared image of the defect of the outer insulating layer specifically includes:
computing a two-dimensional joint probability density PijSetting the initial segmentation threshold value of the external insulation layer defect infrared image as (s, t), segmenting the external insulation layer defect infrared image into a background area and a target area according to the initial segmentation threshold value, and according to the two-dimensional joint probability density PijObtaining the probability w of the background area0Probability w of the target region1And the global mean vector mutAccording to the probability w of the background region0Probability w of the target region1And the global mean vector mutObtaining a dispersion matrix S between the target area and the background areaB(S, t) tracing tr (S) of the dispersion matrixB) As a distance measure function between the background region and the target region class, tr (S) corresponding to each initial segmentation threshold (S, t) is calculated according to the distance measure functionB) When tr (S)B) And the corresponding segmentation threshold (S, T) is the optimal threshold of the defect infrared image of the outer heat-insulating layer when the maximum value is obtained.
Further, the two-dimensional joint probability density PijThe expression of (a) is:
Figure BDA0003467582360000021
wherein L is the gray level of the infrared image with the defects of the outer heat-insulating layer and the average value of the gray levels of the smooth images in the neighborhood thereof, fijThe frequency is the frequency when the gray value is i and the neighborhood gray value is j.
Further, the probability w of the background region0Probability w of the target region1And the global mean vector mutThe expression of (a) is:
Figure BDA0003467582360000031
Figure BDA0003467582360000032
Figure BDA0003467582360000033
wherein, muiAnd mujRespectively representing the gray value of the population and the mean value of the neighborhood gray values.
Further, the dispersion matrix SBThe expression of (s, t) is:
SB(s,t)＝w0[(μ0-μt)(μ0-μt)T]+w1[(μ1-μt)(μ1-μt)T]
wherein, mu0And mu1Mean vectors corresponding to the target area and the background area;
Figure BDA0003467582360000034
Figure BDA0003467582360000035
further, the constructing a sliding matrix to traverse the gray-scale map to select the initial seed point of the region growth specifically includes:
and setting an n multiplied by n sliding matrix to traverse the gray level image of the defect infrared image of the outer heat-insulating layer, calculating the mean value of all pixels in the sliding matrix, and selecting a point marked by the middle value of the region with the maximum mean value as an initial seed point for region growth.
Further, the determining a growth criterion based on the optimal threshold specifically includes:
taking the initial seed point as an initial point, and defining an expression of a growth criterion as follows:
Figure BDA0003467582360000036
wherein S is a segmentation threshold, T is a gray level similarity threshold, f (a, b) is set as a pixel point in a target area, and f is a current gray level mean value;
the updating of the growth criterion specifically comprises:
updated current gray level mean value f and initial gray level mean value
Figure BDA0003467582360000041
Respectively as follows:
Figure BDA0003467582360000042
Figure BDA0003467582360000043
wherein Q is the target area, and n is the number of pixel points.
An infrared image processing device for defects of an external thermal insulation layer of an external wall comprises:
the acquisition module is used for acquiring an infrared image of the defect of the external insulation layer to be processed;
and the processor is used for inputting the infrared image of the defect of the outer insulating layer to be processed into a pre-constructed region growing infrared image segmentation processing model improved based on a two-dimensional OTSU threshold method and outputting the defect image after the segmentation of the outer insulating layer of the outer wall.
A computer-readable storage medium, storing a computer program which, when executed by a processor, implements the steps of a method for infrared image processing of defects in an exterior insulation layer of an exterior wall.
Compared with the prior art, the invention has at least the following beneficial effects: the method for processing the infrared image of the defect of the external thermal insulation layer of the external wall, provided by the invention, comprises the steps of obtaining an infrared image of the defect of the external thermal insulation layer to be processed, inputting the infrared image of the defect of the external thermal insulation layer to be processed into a pre-constructed region growing infrared image segmentation processing model improved based on a two-dimensional OTSU threshold method, and outputting the segmented defect image of the external thermal insulation layer of the external wall. Aiming at the defect of high noise of the infrared image, the optimal segmentation threshold selected based on the two-dimensional OTSU threshold method can generate respective growth criteria for different images, so that the segmentation accuracy is improved, the image can be better segmented to obtain defects under the condition of keeping characteristic details not lost, the initial seed points of the images are automatically determined by using a sliding matrix, the subjective randomness of manually selecting the seed points is avoided, the automatic segmentation capability of the images is enhanced, and the further repair processing work of the defects at the later stage is facilitated.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a top view of an infrared image processing device for defects of an external thermal insulation layer of an external wall in an embodiment;
FIG. 2 is a cross-sectional view of an infrared image processing device for defects of an external insulation layer of an external wall in the embodiment;
FIG. 3 is a flow chart of the method for processing infrared images of defects of the external thermal insulation layer of the external wall of the invention;
FIG. 4 is a flow chart of the method for collecting and processing infrared images of defects of the external thermal insulation layer of the external wall;
FIG. 5 is a diagram of the effect of infrared image processing on defects of the external thermal insulation layer of the external wall, wherein a is an image shot by a 4K high-definition camera or visible to the naked eye, b is a pre-segmentation effect, and c is a final segmentation effect.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As a specific embodiment of the present invention, with reference to fig. 3, 4 and 5, an infrared image processing method for defects of an external thermal insulation layer of an external wall specifically includes the following steps:
and S1, acquiring the infrared image of the defect of the external insulation layer to be processed.
As shown in fig. 1 and fig. 2, in this embodiment, a specific method for obtaining an infrared image of a defect of an external insulation layer to be processed includes: utilize outer heat preservation defect infrared image acquisition device to acquire, outer heat preservation defect infrared image acquisition device includes organism 6, the obstacle perception range finding module 3 that is used for perception obstacle and measuring distance is installed to the platform top of organism 6, a GPS orientation module 4 for the position of location organism 6 and navigation route, a WIFI transmission module 5 for the image information that real-time transmission gathered to local processor, the regional growth infrared image based on two-dimensional OTSU threshold method improvement has been preset among the local processor and has been cut apart the processing model. Four groups of propellers 1 are arranged above the machine body 6 and used for realizing take-off and landing of the unmanned aerial vehicle; four groups of high-speed motors 2 are arranged above the machine body 6 and are used for driving the four groups of propellers 1 to rotate; a power supply module is arranged below the machine body 6 and used for providing power to realize an independent power supply function; a 4K ultra-clear lens is arranged below the machine body 6 and used for shooting the defects of the external thermal insulation layer of the measured external wall and acquiring target information for auxiliary positioning; a radiation heating pipe 9 is arranged below the machine body 6 and used for making up for the deficiency of natural solar radiation; an infrared thermal imager 10 is arranged below the machine body 6 and used for collecting infrared images of the defects of the external heat insulation layer of the external wall of the building; the left and right sides of the body 6 are provided with landing gears 11 for bearing the gravity of the body 6 during parking, taking off and landing on the ground. The device has the collection function of independently accomplishing to building outer wall outer insulation layer defect, on the basis of having compensatied the weak point of traditional collection method, has added plus the heat radiation, has dodged the function of barrier, still can normally accomplish the collection task under the relatively poor condition of external environment, when greatly liberating the manpower, has also improved the quality and the efficiency of building outer wall outer insulation layer defect collection.
And S2, inputting the infrared image of the defect of the outer insulating layer to be processed into a pre-constructed region growing infrared image segmentation processing model improved based on a two-dimensional OTSU threshold method, and outputting the defect image after the segmentation of the outer insulating layer of the outer wall.
Specifically, the construction method of the improved region growing infrared image segmentation processing model based on the two-dimensional OTSU threshold method comprises the following steps:
firstly, acquiring an external insulation layer defect infrared image, determining an optimal threshold value of the external insulation layer defect infrared image, and generating a gray level image of the external insulation layer defect infrared image. Namely, an infrared image with the defects of the M multiplied by N outer insulation layer is subjected to pre-segmentation processing, and a two-dimensional histogram is built by using a two-dimensional OTSU threshold method for graying processing, so that an optimal threshold value is obtained.
Determining an optimal threshold value of the defect infrared image of the outer insulation layer, which specifically comprises the following steps:
computing a two-dimensional joint probability density PijTwo dimensional joint probability density PijThe expression of (a) is:
Figure BDA0003467582360000061
wherein L is the gray level of the infrared image with the defect of the external thermal insulation layer and the average value of the gray levels of the neighborhood smooth images, fijThe frequency is the frequency when the gray value is i and the neighborhood gray value is j;
setting the initial segmentation threshold value of the infrared image with the defects of the external heat preservation layer as (s, t), segmenting the infrared image with the defects of the external heat preservation layer into a background area and a target area according to the initial segmentation threshold value, and according to the two-dimensional joint probability density PijObtaining the probability w of the background area0Probability w of target region1And the global mean vector mutProbability of background region w0Probability w of target region1And the global mean vector mutThe expression of (a) is:
Figure BDA0003467582360000071
Figure BDA0003467582360000072
Figure BDA0003467582360000073
wherein, muiAnd mujRespectively representing the overall gray value and the neighborhood gray average value;
probability w according to background region0Probability w of target region1And the global mean vector mutObtaining a dispersion matrix S between the target area and the background areaB(S, t), dispersion matrix SBThe expression of (s, t) is:
SB(s,t)＝w0[(μ0-μt)(μ0-μt)T]+w1[(μ1-μt)(μ1-μt)T]
wherein, mu0And mu1Mean vectors corresponding to the target area and the background area;
Figure BDA0003467582360000074
Figure BDA0003467582360000075
trace tr (S) of the divergence matrixB) As a distance measure function between the background region and the target region, tr (S) corresponding to each initial segmentation threshold (S, t) is calculated according to the distance measure functionB) When tr (S)B) And the corresponding segmentation threshold (S, T) is the optimal threshold of the defect infrared image of the external heat preservation layer when the maximum value is obtained.
And secondly, constructing a sliding matrix traversal gray level map to select initial seed points of region growth, determining a growth criterion based on an optimal threshold value and updating the growth criterion to obtain an improved region growth infrared image segmentation processing model based on a two-dimensional OTSU threshold value method.
Specifically, constructing a sliding matrix traversal gray level map to select an initial seed point of region growth, specifically comprising:
setting an n multiplied by n sliding matrix to traverse a gray level image of the infrared image of the defect of the outer heat-insulating layer, calculating the mean value of all pixels in the sliding matrix, and selecting a point marked by the middle value of the region with the maximum mean value as an initial seed point for region growth; in this embodiment, a 5 × 5 sliding matrix is provided.
Specifically, the determining the growth criterion based on the optimal threshold specifically includes:
taking the initial seed point as an initial point, and defining an expression of a growth criterion as follows:
Figure BDA0003467582360000081
wherein S is a segmentation threshold, T is a gray level similarity threshold, f (a, b) is set as a pixel point in a target area, and f is a current gray level mean value;
when the pixel point meets the growth criterion, in order to prevent the algorithm from generating over-segmentation or under-segmentation due to the fixed mean value, the gray mean value needs to be updated after the growth is completed each time.
Updated current gray level mean value f and initial gray level mean value
Figure BDA0003467582360000082
Respectively as follows:
Figure BDA0003467582360000083
Figure BDA0003467582360000084
wherein Q is the target area, and n is the number of pixel points.
And stopping growing until no pixel points meeting the requirement of the criterion exist around the seed pixel, and finishing the segmentation processing of the target image.
The present invention provides, in one embodiment, a computer device comprising a processor and a memory for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium. The Processor may be a Central Processing Unit (CPU), or may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable gate array (FPGA) or other Programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc., which is a computing core and a control core of the terminal, and is adapted to implement one or more instructions, and is specifically adapted to load and execute one or more instructions to implement a corresponding method flow or a corresponding function; the processor provided by the embodiment of the invention can be used for operating the infrared image processing method for the defects of the external thermal insulation layer of the external wall.
In one embodiment of the invention, the infrared image processing method for the defects of the external thermal insulation layer of the external wall can be stored in a computer readable storage medium if the infrared image processing method is realized in the form of a software functional unit and is sold or used as an independent product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. Computer-readable storage media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data.
The computer storage media may be any available media or data storage device that can be accessed by a computer, including but not limited to magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memories (NANDFLASH), Solid State Disks (SSDs)), etc.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. An infrared image processing method for defects of an external thermal insulation layer of an external wall is characterized by comprising the following steps:
acquiring an infrared image of the defect of the external insulation layer to be treated;
and inputting the infrared image of the defect of the outer insulating layer to be processed into a pre-constructed region growing infrared image segmentation processing model improved based on a two-dimensional OTSU threshold method, and outputting the defect image after the segmentation of the outer insulating layer of the outer wall.
2. The method for processing the infrared image of the defect of the external thermal insulation layer of the external wall according to claim 1, wherein the method for constructing the region growing infrared image segmentation processing model improved based on the two-dimensional OTSU threshold method comprises the following steps:
acquiring an external insulation layer defect infrared image, determining an optimal threshold value of the external insulation layer defect infrared image, and generating a gray scale image of the external insulation layer defect infrared image;
and constructing a sliding matrix to traverse the gray-scale map to select initial seed points of region growth, determining a growth criterion based on the optimal threshold value and updating the growth criterion to obtain the improved region growth infrared image segmentation processing model based on the two-dimensional OTSU threshold value method.
3. The method for processing the infrared image of the defect of the external thermal insulation layer of the external wall according to claim 2, wherein the determining of the optimal threshold value of the infrared image of the defect of the external thermal insulation layer specifically comprises:
computing a two-dimensional joint probability density PijSetting the initial segmentation threshold value of the external insulation layer defect infrared image as (s, t), segmenting the external insulation layer defect infrared image into a background area and a target area according to the initial segmentation threshold value, and according to the two-dimensional joint probability density PijObtaining the probability w of the background area0Probability w of the target region1And the global mean vector mutAccording to the probability w of the background region0Probability w of the target region1And the global mean vector mutObtaining a dispersion matrix S between the target area and the background areaB(S, t) tracing tr (S) of the dispersion matrixB) As a distance measure function between the background region and the target region class, tr (S) corresponding to each initial segmentation threshold (S, t) is calculated according to the distance measure functionB) When tr (S)B) And the corresponding segmentation threshold (S, T) is the optimal threshold of the defect infrared image of the outer heat-insulating layer when the maximum value is obtained.
4. The infrared image processing method for the defects of the external thermal insulation layer of the external wall as claimed in claim 3, wherein the two-dimensional joint probability density pijThe expression of (a) is:
Figure FDA0003467582350000021
wherein L is the gray level of the infrared image with the defects of the outer heat-insulating layer and the average value of the gray levels of the smooth images in the neighborhood thereof, fijThe frequency is the frequency when the gray value is i and the neighborhood gray value is j.
5. The infrared image processing method for the defects of the external thermal insulation layer of the external wall as claimed in claim 4, wherein the probability w of the background area0Probability w of the target region1And the global mean vector mutThe expression of (a) is:
Figure FDA0003467582350000022
Figure FDA0003467582350000023
Figure FDA0003467582350000024
wherein, muiAnd mujRespectively representing the gray value of the population and the mean value of the neighborhood gray values.
6. The infrared image processing method for the defects of the external thermal insulation layer of the external wall as claimed in claim 5, wherein the dispersion matrix S isBThe expression of (s, t) is:
SB(s，t)＝w0[(μ0-μt)(μ0-μt)T]+w1[(μ1-μt)(μ1-μt)T]
wherein, mu0And mu1Mean vectors corresponding to the target area and the background area;
Figure FDA0003467582350000025
Figure FDA0003467582350000026
7. the infrared image processing method for the defects of the external thermal insulation layer of the external wall as claimed in claim 3, wherein the constructing of the sliding matrix traversing the gray-scale map to select the initial seed points of the region growth specifically comprises:
and setting an n multiplied by n sliding matrix to traverse the gray level image of the defect infrared image of the outer heat-insulating layer, calculating the mean value of all pixels in the sliding matrix, and selecting a point marked by the middle value of the region with the maximum mean value as an initial seed point for region growth.
8. The infrared image processing method for the defects of the external thermal insulation layer of the external wall as claimed in claim 3, wherein the determining of the growth criterion based on the optimal threshold specifically comprises:
taking the initial seed point as an initial point, and defining an expression of a growth criterion as follows:
Figure FDA0003467582350000031
wherein S is a segmentation threshold, T is a gray level similarity threshold, f (a, b) is set as a pixel point in a target area, and f is a current gray level mean value;
the updating of the growth criterion specifically comprises:
updated current gray level mean value f and initial gray level mean value
Figure FDA0003467582350000032
Respectively as follows:
Figure FDA0003467582350000033
Figure FDA0003467582350000034
wherein Q is the target area, and n is the number of pixel points.
9. The utility model provides an outer heat preservation defect infrared image processing apparatus of outer wall which characterized in that includes:
the acquisition module is used for acquiring an infrared image of the defect of the external insulation layer to be processed;
and the processor is used for inputting the infrared image of the defect of the outer insulating layer to be processed into a pre-constructed region growing infrared image segmentation processing model improved based on a two-dimensional OTSU threshold method and outputting the defect image after the segmentation of the outer insulating layer of the outer wall.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of a method for infrared image processing of defects of an exterior insulation layer of an exterior wall according to any one of claims 1 to 8.
CN202210033970.6A 2022-01-12 2022-01-12 Infrared image processing method and device for defects of external thermal insulation layer of external wall and storage medium Pending CN114387253A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210033970.6A CN114387253A (en) 2022-01-12 2022-01-12 Infrared image processing method and device for defects of external thermal insulation layer of external wall and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210033970.6A CN114387253A (en) 2022-01-12 2022-01-12 Infrared image processing method and device for defects of external thermal insulation layer of external wall and storage medium

Publications (1)

Publication Number Publication Date
CN114387253A true CN114387253A (en) 2022-04-22

Family

ID=81200961

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210033970.6A Pending CN114387253A (en) 2022-01-12 2022-01-12 Infrared image processing method and device for defects of external thermal insulation layer of external wall and storage medium

Country Status (1)

Country Link
CN (1) CN114387253A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116818830A (en) * 2023-08-29 2023-09-29 山东津庭名企建材有限公司 Thermal insulation performance detection method for low-carbon building material
CN117237338A (en) * 2023-11-10 2023-12-15 山东天意高科技有限公司 Defect identification method for building external heat-insulating layer hollowing
CN117966982A (en) * 2024-03-28 2024-05-03 四川赛尔科美新材料科技有限公司 Heat preservation layer based on silicon substrate heat preservation material and laying method thereof
CN117966982B (en) * 2024-03-28 2024-06-07 四川赛尔科美新材料科技有限公司 Heat preservation layer based on silicon substrate heat preservation material and laying method thereof

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116818830A (en) * 2023-08-29 2023-09-29 山东津庭名企建材有限公司 Thermal insulation performance detection method for low-carbon building material
CN116818830B (en) * 2023-08-29 2023-12-01 山东津庭名企建材有限公司 Thermal insulation performance detection method for low-carbon building material
CN117237338A (en) * 2023-11-10 2023-12-15 山东天意高科技有限公司 Defect identification method for building external heat-insulating layer hollowing
CN117237338B (en) * 2023-11-10 2024-01-30 山东天意高科技有限公司 Defect identification method for building external heat-insulating layer hollowing
CN117966982A (en) * 2024-03-28 2024-05-03 四川赛尔科美新材料科技有限公司 Heat preservation layer based on silicon substrate heat preservation material and laying method thereof
CN117966982B (en) * 2024-03-28 2024-06-07 四川赛尔科美新材料科技有限公司 Heat preservation layer based on silicon substrate heat preservation material and laying method thereof

Similar Documents

Publication Publication Date Title
CN109522788B (en) City range extraction method and device based on random forest classification algorithm and electronic equipment
CN111460984B (en) Global lane line detection method based on key points and gradient equalization loss
CN114387253A (en) Infrared image processing method and device for defects of external thermal insulation layer of external wall and storage medium
CN102346015A (en) Method for measuring icing thickness of insulator of power transmission line based on video difference analysis
CN111191570B (en) Image recognition method and device
CN111369495B (en) Panoramic image change detection method based on video
CN103714541A (en) Method for identifying and positioning building through mountain body contour area constraint
CN111862013B (en) Insulator detection method, device and equipment based on deep convolutional neural network
CN113689445B (en) High-resolution remote sensing building extraction method combining semantic segmentation and edge detection
CN109087323A (en) A kind of image three-dimensional vehicle Attitude estimation method based on fine CAD model
CN114089330B (en) Indoor mobile robot glass detection and map updating method based on depth image restoration
CN114241364A (en) Method for quickly calibrating foreign object target of overhead transmission line
CN114565675A (en) Method for removing dynamic feature points at front end of visual SLAM
CN114937130B (en) Topographic map mapping method, device, equipment and storage medium
CN115240089A (en) Vehicle detection method of aerial remote sensing image
CN106683125A (en) RGB-D image registration method based on 2D/3D mode switching
CN113971669A (en) Three-dimensional detection system applied to pipeline damage identification
CN113313107A (en) Intelligent detection and identification method for multiple types of diseases on cable surface of cable-stayed bridge
CN115578326A (en) Road disease identification method, system, equipment and storage medium
CN116563262A (en) Building crack detection algorithm based on multiple modes
CN113963314A (en) Rainfall monitoring method and device, computer equipment and storage medium
Dong et al. Pixel-level intelligent segmentation and measurement method for pavement multiple damages based on mobile deep learning
CN116363302B (en) Pipeline three-dimensional reconstruction and pit quantification method based on multi-view geometry
CN113570554A (en) Single image visibility detection method based on scene depth
CN115984360B (en) Method and system for calculating length of dry beach based on image processing

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