CN109523544B - Building outer wall quality defect detection system and method thereof - Google Patents
Building outer wall quality defect detection system and method thereof Download PDFInfo
- Publication number
- CN109523544B CN109523544B CN201811420575.3A CN201811420575A CN109523544B CN 109523544 B CN109523544 B CN 109523544B CN 201811420575 A CN201811420575 A CN 201811420575A CN 109523544 B CN109523544 B CN 109523544B
- Authority
- CN
- China
- Prior art keywords
- image
- color
- wall
- area
- pixels
- 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.)
- Active
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Radiation Pyrometers (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method for detecting quality defects of an external wall of a building, which belongs to the technical field of building detection and comprises the following steps: s1: collecting a wall color image; s2: comparing the color similarity of the collected color images, and dividing pixels with high similarity into pixel regions; s3: collecting infrared images of the wall body; s4: dividing the infrared image into infrared image areas in the same manner as the step S2 of dividing the pixel areas; s5: and carrying out temperature data statistics on the infrared image area, calculating the temperature threshold of the temperature data in the infrared image area by adopting an iterative method, and marking the area which exceeds the temperature threshold range of the area as a defect area.
Description
Technical Field
The invention relates to the field of outer wall quality detection, in particular to a system and a method for detecting quality defects of an outer wall of a building.
Background
In order to beautify the environment, the selection of exterior wall facing materials in urban buildings has become one of the main sections for decorating houses, but due to the defect of the bonding quality of exterior wall facing bricks, the falling of the exterior wall facing bricks sometimes happens to hurt people. The analysis reasons are mainly that the building is influenced by factors such as construction technology quality, wind, mechanical vibration, temperature difference, rainwater erosion and the like after being put into use, the phenomena of falling, cracking, falling and the like of the bonding strength of the exterior wall facing material and the substrate occur, and if the phenomena cannot be found in time, the potential safety hazard caused by the falling of the exterior wall facing bricks of the high-rise building is larger. With the continuous improvement of the detection technology of the construction engineering, the infrared technology provides a new detection method for the quality detection of the construction industry. In order to guarantee the life and property safety of people, improve the accuracy of the detection of the pasting quality of the exterior wall facing bricks, solve the limitation of the traditional detection method (a tapping method, a daily measurement method, a drawing method and the like), technical regulation for detecting the pasting quality of the exterior wall facing of the building by an infrared thermal imaging method (JGJ/T277-2012) is issued by the Ministry of construction 1 month in 2012, and the pasting quality of the exterior wall facing bricks of the building can be detected by using an infrared thermal imager. The thermal image obtained through infrared thermal image detection is recorded and displayed in a direct visual mode, the detection result can be analyzed in a high-precision mode through analyzing the thermal image, the detection accuracy, the detection effectiveness and the detection rationality are greatly improved, and the detection of the pasting quality of the facing bricks of the exterior walls of the buildings becomes more scientific, more advanced and more practical.
However, thermal infrared imagers are not suitable for tile facing applications using color-mixed facing tiles and for facing applications using insulation between exterior wall bodies and exterior facing tiles. The analysis reason is that the detection is influenced by the different abilities of absorbing solar radiation due to the larger color difference of the mixed color facing bricks.
Disclosure of Invention
The invention aims to provide a method for detecting the quality defect of an outer wall of a building, which can be used for carrying out defect analysis on a mixed color wall.
The above object of the present invention is achieved by the following technical solutions:
a method for detecting quality defects of an exterior wall of a building, the method comprising: s1: collecting a wall color image; s2: comparing the color similarity of the collected color images, and dividing pixels with high similarity into pixel regions; s3: collecting infrared images of the wall body; s4: dividing the infrared image into infrared image areas in the same manner as the step S2 of dividing the pixel areas; s5: and carrying out temperature data statistics on the infrared image area, calculating the temperature threshold of the temperature data in the infrared image area by adopting an iterative method, and marking the area which exceeds the temperature threshold range of the area as a defect area.
Further, the color image is aligned with the infrared image.
Further, the specific method for dividing the pixels with high similarity into pixel regions is as follows: s201, selecting a first pixel which is not distributed with a partition area as a seed pixel in a mode of from left to right and from top to bottom; s202, checking the pixels which are not distributed with the segmentation areas in the 8 adjacent regions of the seed pixels, determining whether the pixels belong to the region where the seed pixels are located according to a color similarity determination rule, and if the color similarity determination condition is met, distributing the pixels to the region and giving a mark; s203, when the segmentation of a region is not completed, the process of the step S202 is continuously repeated until the region is defined by the boundary of the image or the pixels which do not meet the similarity condition; s204: when a region is grown to the maximum, that is, no pixels near the edge of the region satisfy the similarity determination condition, the next process is performed as the case may be, i.e., if there are unmarked color pixels in the image, the process returns to step S201 to continue the next region growing process, and if the pixels of the entire image have been allocated to the corresponding region, the image segmentation process is ended.
Further, an iterative method is adopted to calculate the temperature threshold of the infrared image, and the specific algorithm flow of the iterative method is as follows: s501: setting a threshold value T0(ii) a S502: by T0The image is divided into two parts, denoted G1(x, y) and G2(x, y), wherein:
G1(x，y)＝{f(x，y)|f(x，y)＜T0}
G2(x，y)＝{f(x，y)|f(x，y)＞T0}
s503: the mean of these two fractions was calculated separately:
redefining the threshold value S504:
threshold value T using shape0Recalculating according to the steps S501-S502, and repeating the steps for multiple iterations to obtain the threshold T0And stopping after the convergence is reached after the stability is within a certain range.
Further, the boundary values of the temperature threshold range are 95% and 105% of the temperature threshold.
The invention also aims to provide a method for detecting the quality defect of the building outer wall, which can be used for carrying out defect analysis on the mixed color wall.
The second purpose of the invention is realized by the following technical scheme:
a building exterior wall quality defect detection system, the system comprising: the camera is used for collecting the wall color image; the infrared camera is used for collecting the infrared image of the wall; the processor is used for comparing the color similarity of the collected color images and dividing the pixels with high similarity into pixel areas; dividing the infrared image into infrared image areas in the same way as the pixel areas are divided; and carrying out temperature data statistics on the infrared image area, calculating the temperature threshold of the temperature data in the infrared image area by adopting an iterative method, and marking the area which exceeds the temperature threshold range of the area as a defect area.
In conclusion, the invention has the following beneficial effects: the invention firstly divides the outer wall of the mixed color into pixel areas based on the color similarity coefficient color image segmentation method, then divides the infrared image into infrared image areas in a pixel area division mode, respectively compares the temperature threshold value range of the infrared image areas, and finds out the defect areas. The problem that the infrared image detection cannot be carried out due to the fact that the heat absorption conditions of the mixed-color outer wall are different due to the fact that the colors of all parts are different is solved.
Drawings
FIG. 1 is a block diagram of a method for detecting quality defects of an exterior wall of a building according to an embodiment of the present invention;
FIG. 2 is a color image of an exterior wall according to an embodiment of the present invention;
FIG. 3 is an infrared image of an exterior wall after threshold determination according to an embodiment of the present invention;
fig. 4 is a system block diagram of a building exterior wall quality defect detection system according to an embodiment of the invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be described below with reference to the accompanying drawings.
In a first aspect, the present invention discloses a method for detecting quality defects of an exterior wall of a building, as shown in fig. 1, the method includes:
s1: collecting a wall color image;
s2: comparing the color similarity of the collected color images, and dividing pixels with high similarity into pixel regions;
specifically, the present embodiment adopts document [15 ] according to the purpose and requirement of color image segmentation]The color similarity measurement method proposed in (1) to determine the color similarity between two pixels. Let two pixel color vectors f and h in RGB color space, f ═ f1, f2, f3) ', h ═ h1, h2, h 3)'. The color similarity coefficient between two color vectors is defined as KC(f,h)；
KC(f，h)＝λRKR(f，h)+λBKB(f，h)
Wherein, KR(f,h)Is the chroma saturation similarity coefficient between the two colors f and h;
<f，h>＝f′h
in the formula, KB(f,h)Is the brightness similarity factor between the two colors f and h.
In the formula, λR,λBCorresponding weights, λ, of the chroma saturation similarity coefficient and the luminance similarity coefficient, respectivelyR+λB1, where λ is setRGreater than λBThis is because the chrominance and saturation are dominant and the luminance is relatively subordinate to the human visual perception characteristics. In practical application, λ is setR＝0.85,λB＝0.15。
Judging whether the two colors are similar according to KC(f,h)Is determined if KC(f,h)>T, then f, h, the two colors represented are similar, otherwise they are dissimilar. T here is a determination threshold, and T is 0. ltoreq. T.ltoreq.1. If the T value is set to be large, an under-segmentation image is generated; if the setting is small, an over-segmented image is generated. In practical application, let T be 0.985.
Based on the above color similarity determination rule, the embodiments of the invention herein employ a region growing method to realize segmentation of the entire color image. Starting from the first seed pixel of the color image, a region is grown from this seed pixel. This seed pixel is compared with its undivided 8-neighborhood pixels, and any neighborhood pixels that satisfy the color similarity determination condition are assigned to the same color region and given a label. This neighborhood comparison step is repeated for each pixel assigned to a given region until the region is bounded by the boundaries of the image or pixels that do not satisfy similar conditions. The next seed pixel will be selected from left to right, top to bottom across the image, being the first unassigned pixel in the last growth region. The region growing step according to the above is again used until the second region is completely divided. This process is repeated until each pixel in the image belongs to a region and is marked. The segmentation algorithm is summarized as the following steps:
s201, selecting a first pixel which is not distributed with a partition area as a seed pixel in a mode of from left to right and from top to bottom;
s202, checking the pixels which are not distributed with the segmentation areas in the 8 adjacent regions of the seed pixels, determining whether the pixels belong to the region where the seed pixels are located according to a color similarity determination rule, and if the color similarity determination condition is met, distributing the pixels to the region and giving a mark;
s203, when the segmentation of a region is not completed, the process of the step S202 is continuously repeated until the region is defined by the boundary of the image or the pixels which do not meet the similarity condition;
s204: when a region is grown to the maximum, that is, no pixels near the edge of the region satisfy the similarity determination condition, the next process is performed as the case may be, i.e., if there are unmarked color pixels in the image, the process returns to step S201 to continue the next region growing process, and if the pixels of the entire image have been allocated to the corresponding region, the image segmentation process is ended.
S3: collecting infrared images of the wall body;
s4: dividing the infrared image into infrared image areas in the same manner as the step S2 of dividing the pixel areas;
specifically, for example, in a mixed color outer wall shown in fig. 2, the oblique line area and the blank area represent different colors. Because the colors of different areas on the outer wall are different, the degree of solar radiation received by each area is different, and therefore the temperature of each area is different. The infrared image areas are thus segmented according to the color of the outer wall, so that areas of different colors can be analyzed in zones on the basis of infrared detection. It should be noted that the color image and the infrared image are aligned, i.e. the color image of the outer wall to be detected and the infrared image can be overlapped.
S5: and carrying out temperature data statistics on the infrared image area, calculating the temperature threshold of the temperature data in the infrared image area by adopting an iterative method, and marking the area which exceeds the temperature threshold range of the area as a defect area.
Specifically, the temperature data in the infrared image is subjected to statistical analysis by using MATALB, and the temperature threshold of the infrared image is calculated by adopting an iterative method, wherein the specific algorithm flow of the iterative method is as follows:
s501: setting a threshold value T0；
S502: by T0The image is divided into two parts, denoted G1(x, y) and G2(x, y), wherein:
G1(x，y)＝{f(x，y)|f(x，y)＜T0}
G2(x，y)＝{f(x，y)|f(x，y)＞T0}
s503: the mean of these two fractions was calculated separately:
redefining the threshold value S504:
threshold value T using shape0Recalculating according to the steps S501-S502, and repeating the steps for multiple iterations to obtain the threshold T0And stopping after the convergence is reached after the stability is within a certain range.
The boundary values of the temperature threshold range are 95% and 105% of the temperature threshold, and if the temperature threshold is exceeded, the defect of the outer wall is indicated. For example, if the temperature threshold is 40 ℃, the temperature threshold range is 38 ℃ to 42 ℃. Generally, the surface temperature of the external wall panel (brick) will rise in sunshine, and the temperature of the hollowing part is higher than that of the normal part; when the outside surface insolation decreases or the air temperature decreases, the opposite is true. Therefore, if the outer wall has bonding defect parts such as falling, hollowing and the like, the bonding defect parts are expressed as 'hot spots' or 'cold spots' on the infrared image, the detection result is visual and reliable, the infrared thermal image characteristic map of the outer wall is analyzed, the theoretical calculation is carried out on the infrared thermal image characteristic map, the bonding quality of the outer wall can be determined, and the defects of the outer wall veneer can be accurately judged. And carrying out infrared thermographic characteristic analysis on areas with different colors by combining image segmentation based on color similarity, thereby realizing defect detection on the mixed color outer wall. The finally obtained image after defect detection is shown in fig. 3, where a blank area represents a defect area and a diagonal line represents a normal area.
The invention also provides a system for detecting the quality defect of the outer wall of the building, which is shown as a system block diagram in fig. 4 and comprises the following components:
the camera is used for collecting the wall color image;
the infrared camera is used for collecting the infrared image of the wall;
the processor is used for comparing the color similarity of the collected color images and dividing the pixels with high similarity into pixel areas; dividing the infrared image into infrared image areas in the same way as the pixel areas are divided; and carrying out temperature data statistics on the infrared image area, calculating the temperature threshold of the temperature data in the infrared image area by adopting an iterative method, and marking the area which exceeds the temperature threshold range of the area as a defect area.
The method for detecting the quality defect of the outer wall of the building by the processor is the same as the method of the first aspect.
Claims (6)
1. A method for detecting quality defects of an external wall of a building is characterized by comprising the following steps:
s1: collecting a wall color image;
s2: comparing the color similarity of the collected color images, and dividing pixels with high similarity into pixel regions;
s3: collecting infrared images of the wall body;
s4: the infrared image area is divided according to the color of the outer wall, so that the areas with different colors can be subjected to partition analysis based on infrared detection; the positions of the color image and the infrared image are aligned, namely the color image of the outer wall to be detected is superposed with the infrared image;
s5: and carrying out temperature data statistics on the infrared image area, calculating the temperature threshold of the temperature data in the infrared image area by adopting an iterative method, and marking the area which exceeds the temperature threshold range of the area as a defect area.
2. The method for detecting the quality defect of the exterior wall of the building as claimed in claim 1, wherein the color image is aligned with the infrared image.
3. The method for detecting the quality defect of the exterior wall of the building as claimed in claim 1, wherein the specific method for dividing the pixels with high similarity into pixel areas is as follows:
s201, selecting a first pixel which is not distributed with a partition area as a seed pixel in a mode of from left to right and from top to bottom;
s202, checking the pixels which are not distributed with the segmentation areas in the 8 adjacent regions of the seed pixels, determining whether the pixels belong to the region where the seed pixels are located according to a color similarity determination rule, and if the color similarity determination condition is met, distributing the pixels to the region and giving a mark;
s203, when the segmentation of a region is not completed, the process of the step S202 is continuously repeated until the region is defined by the boundary of the image or the pixels which do not meet the similarity condition;
s204: when a region is grown to the maximum, that is, no pixels near the edge of the region satisfy the similarity determination condition, the next process is performed as the case may be, i.e., if there are unmarked color pixels in the image, the process returns to step S201 to continue the next region growing process, and if the pixels of the entire image have been allocated to the corresponding region, the image segmentation process is ended.
4. The method for detecting the quality defect of the outer wall of the building according to claim 1, wherein the temperature threshold of the infrared image is calculated by adopting an iterative method, and the specific algorithm flow of the iterative method is as follows:
s501: setting a threshold value T0；
S502: by T0The image is divided into two parts, denoted G1(x, y) and G2(x, y), wherein:
G1(x，y)＝{f(x，y)|f(x，y)＜T0}
G2(x，y)＝{f(x，y)|f(x，y)＞T0}
s503: the mean of these two fractions was calculated separately:
redefining the threshold value S504:
threshold value T using shape0Recalculating according to the steps S501-S502, and repeating the steps for multiple iterations to obtain the threshold T0And stopping after the convergence is reached after the stability is within a certain range.
5. The method as claimed in claim 4, wherein the boundary value of the temperature threshold range is 95% and 105% of the temperature threshold.
6. A building exterior wall quality defect detection system, the system comprising: the camera is used for collecting the wall color image;
the infrared camera is used for collecting the infrared image of the wall;
the processor is used for comparing the color similarity of the collected color images and dividing the pixels with high similarity into pixel areas; dividing infrared image areas according to the colors of the outer wall, so that the areas with different colors can be subjected to subarea analysis based on infrared detection, wherein the positions of the color image and the infrared image are aligned, namely the color image of the outer wall to be detected is superposed with the infrared image; and carrying out temperature data statistics on the infrared image area, calculating the temperature threshold of the temperature data in the infrared image area by adopting an iterative method, and marking the area which exceeds the temperature threshold range of the area as a defect area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811420575.3A CN109523544B (en) | 2018-11-26 | 2018-11-26 | Building outer wall quality defect detection system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811420575.3A CN109523544B (en) | 2018-11-26 | 2018-11-26 | Building outer wall quality defect detection system and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109523544A CN109523544A (en) | 2019-03-26 |
| CN109523544B true CN109523544B (en) | 2021-02-26 |
Family
ID=65794364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811420575.3A Active CN109523544B (en) | 2018-11-26 | 2018-11-26 | Building outer wall quality defect detection system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109523544B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110415241A (en) * | 2019-08-02 | 2019-11-05 | 同济大学 | A kind of surface of concrete structure quality determining method based on computer vision |
| CN110411820A (en) * | 2019-08-05 | 2019-11-05 | 重庆建工第三建设有限责任公司 | A kind of Construction Quality safe risk detecting system and its method online |
| CN110658495B (en) * | 2019-08-22 | 2023-08-11 | 北京天睿视迅科技有限公司 | Position detection method and device |
| CN110889327B (en) * | 2019-10-16 | 2023-05-26 | 南京航空航天大学 | Intelligent detection method for sewage outlet around water area based on thermal infrared image |
| 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 |
| CN117689660B (en) * | 2024-02-02 | 2024-05-14 | 杭州百子尖科技股份有限公司 | Vacuum cup temperature quality inspection method based on machine vision |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101451970A (en) * | 2008-12-18 | 2009-06-10 | 上海交通大学 | Non-contact nondestructive detecting method for hollow drum position of ancient mural painting |
| CN103163181A (en) * | 2013-03-21 | 2013-06-19 | 山东省计算中心 | Automatic thermotechnical area identification method based on outdoor scene infrared image of building |
| CN103163151A (en) * | 2013-03-21 | 2013-06-19 | 山东省计算中心 | Accurate building thermotechnical defect positioning method based on infrared image |
| CN106018420A (en) * | 2016-07-05 | 2016-10-12 | 江苏方建质量鉴定检测有限公司 | Infrared quality detecting method for hollowing defects of outer wall |
| CN108535321A (en) * | 2018-03-30 | 2018-09-14 | 吉林建筑大学 | A kind of building thermal technique method for testing performance based on three-dimensional infrared thermal imaging technique |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10376600B2 (en) * | 2016-03-03 | 2019-08-13 | Gholam A. Peyman | Early disease detection and therapy |
-
2018
- 2018-11-26 CN CN201811420575.3A patent/CN109523544B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101451970A (en) * | 2008-12-18 | 2009-06-10 | 上海交通大学 | Non-contact nondestructive detecting method for hollow drum position of ancient mural painting |
| CN103163181A (en) * | 2013-03-21 | 2013-06-19 | 山东省计算中心 | Automatic thermotechnical area identification method based on outdoor scene infrared image of building |
| CN103163151A (en) * | 2013-03-21 | 2013-06-19 | 山东省计算中心 | Accurate building thermotechnical defect positioning method based on infrared image |
| CN106018420A (en) * | 2016-07-05 | 2016-10-12 | 江苏方建质量鉴定检测有限公司 | Infrared quality detecting method for hollowing defects of outer wall |
| CN108535321A (en) * | 2018-03-30 | 2018-09-14 | 吉林建筑大学 | A kind of building thermal technique method for testing performance based on three-dimensional infrared thermal imaging technique |
Non-Patent Citations (3)
| Title |
|---|
| ".红外热成像及图像处理技术在建筑物缺陷检测方面的应用";杨燕萍 等;《新型建筑材料》;20111231;第38卷(第12期);第83-86页 * |
| "Study on Several Issues of the Infrared-Thermography Method on Detecting the Defects of External Wall";Ji Tong Jiang 等;《Advanced Materials Research》;20120131;第446-449卷;第2983-2987页 * |
| "红外热像法检测建筑节能缺陷的应用研究";杨晓虹 等;《工程质量》;20110331;第29卷(第03期);第57-59页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109523544A (en) | 2019-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109523544B (en) | Building outer wall quality defect detection system and method thereof | |
| CN111127318B (en) | Panoramic image splicing method in airport environment | |
| CN111681289A (en) | Fair-faced concrete color difference analysis/detection method and system | |
| CN112785579A (en) | Concrete crack identification method based on image processing technology | |
| CN108596849A (en) | A kind of single image to the fog method based on sky areas segmentation | |
| TWI324011B (en) | Method for compensating pixel of image | |
| CN108535321A (en) | A kind of building thermal technique method for testing performance based on three-dimensional infrared thermal imaging technique | |
| EP1359543A3 (en) | Method for detecting subject matter regions in images | |
| CN104618703B (en) | A kind of white balance adjustment method | |
| TWI532385B (en) | White balance method and apparatus thereof | |
| JP2008277899A (en) | White balance adjustment device, imaging device, and white balance adjusting program | |
| JP5044755B1 (en) | Image processing apparatus and building image diagnostic apparatus | |
| CN104732578A (en) | Building texture optimization method based on oblique photograph technology | |
| CN115641327B (en) | Building engineering quality supervision and early warning system based on big data | |
| CN103163151A (en) | Accurate building thermotechnical defect positioning method based on infrared image | |
| CN103198486A (en) | Depth image enhancement method based on anisotropic diffusion | |
| CN106815602B (en) | runway FOD image detection method and device based on multi-level feature description | |
| CN115144434A (en) | Method for detecting defects of building outer wall by using infrared thermal imaging technology | |
| JP5017507B1 (en) | Image processing method, image processing apparatus, building image diagnosis method, and building image diagnosis apparatus | |
| CN108305216A (en) | A kind of image magnification method of bilateral four interpolation | |
| Sithole et al. | Determination of urban thermal characteristics on an urban/rural land cover gradient using remotely sensed data | |
| CN112487950A (en) | Intelligent recognition system and method for defects of bare bricks | |
| CN109525828A (en) | A kind of discrepancy tunnel or driving recording auto white balance method when going out walking in the night | |
| CN108898080A (en) | A kind of crack connection method based on ridge line neighborhood evaluation model | |
| Previtali et al. | Generation of a GIS-based environment for infrared thermography analysis of buildings |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |