CN111223074A - Method for detecting concrete defects at top of concrete column member - Google Patents

Method for detecting concrete defects at top of concrete column member Download PDF

Info

Publication number
CN111223074A
CN111223074A CN201911381075.8A CN201911381075A CN111223074A CN 111223074 A CN111223074 A CN 111223074A CN 201911381075 A CN201911381075 A CN 201911381075A CN 111223074 A CN111223074 A CN 111223074A
Authority
CN
China
Prior art keywords
image
gray
pixel point
frequency coefficient
concrete
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.)
Granted
Application number
CN201911381075.8A
Other languages
Chinese (zh)
Other versions
CN111223074B (en
Inventor
朱世平
袁慧萍
邵海东
慈强
连云飞
卜勇
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.)
Ningxia Institute Of Building Research Co ltd
Original Assignee
Ningxia Institute Of Building Research Co ltd
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 Ningxia Institute Of Building Research Co ltd filed Critical Ningxia Institute Of Building Research Co ltd
Priority to CN201911381075.8A priority Critical patent/CN111223074B/en
Publication of CN111223074A publication Critical patent/CN111223074A/en
Application granted granted Critical
Publication of CN111223074B publication Critical patent/CN111223074B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30132—Masonry; Concrete

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Image Processing (AREA)

Abstract

The invention provides a method for detecting concrete defects at the top of a concrete column member, which comprises the steps of firstly obtaining a defect image of concrete at the top of the concrete column member; then, extracting the characteristics of the defect image to obtain the characteristic data of the defect image; and finally, determining the type of the defects of the concrete at the top of the concrete column member according to the characteristic data. The invention provides a method for detecting concrete defects at the top of a concrete column member in an image detection mode, which effectively solves the problem of low efficiency in the traditional detection mode.

Description

Method for detecting concrete defects at top of concrete column member
Technical Field
The invention relates to the field of detection, in particular to a method for detecting concrete defects at the top of a concrete column member.
Background
In the prior art, the detection of the concrete defects is usually carried out in a human eye detection mode, so that the experience of detection personnel is examined, and the efficiency is low.
Disclosure of Invention
Aiming at the problems, the invention provides a method for detecting concrete defects at the top of a concrete column member, which comprises the following steps:
acquiring a defect image of concrete at the top of the concrete column member;
extracting the characteristics of the defect image to obtain the characteristic data of the defect image;
and determining the type of the defects existing in the concrete on the top of the concrete column member according to the characteristic data.
Preferably, the extracting the features of the defect image to obtain the feature data of the defect image includes:
carrying out graying processing on the defect image to obtain a grayed image;
carrying out noise reduction processing on the gray images to obtain noise reduction images;
performing illumination correction on the noise-reduced image to obtain a corrected image;
carrying out edge detection on the corrected image to obtain an edge detection image;
removing isolated noise points from the edge detection image to obtain a noise point removed image;
and performing feature extraction on the noise point removed image to obtain feature data of the noise point removed image.
Preferably, the graying the defect image to obtain a grayed image includes:
and performing graying processing on the defect image by using a weighted average method to obtain a grayed image.
Preferably, the graying the defect image to obtain a grayed image includes:
and performing graying processing on the defect image by using a weighted average method to obtain a grayed image.
Preferably, the performing noise reduction processing on the grayed image to obtain a noise-reduced image includes:
dividing the gray-scale image into N blocks with equal areas;
and respectively performing wavelet denoising processing on each block.
The invention has the beneficial effects that:
the invention provides a method for detecting concrete defects at the top of a concrete column member in an image detection mode, which effectively solves the problem of low efficiency in the traditional detection mode.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a diagram of an exemplary embodiment of a method of detecting concrete defects in a top portion of a concrete column member according to the present invention.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the method for detecting concrete defects on the top of a concrete column member of the present invention comprises the following steps:
acquiring a defect image of concrete at the top of the concrete column member;
extracting the characteristics of the defect image to obtain the characteristic data of the defect image;
and determining the type of the defects existing in the concrete on the top of the concrete column member according to the characteristic data.
In an embodiment, the performing feature extraction on the defect image to obtain feature data of the defect image includes:
carrying out graying processing on the defect image to obtain a grayed image;
carrying out noise reduction processing on the gray images to obtain noise reduction images;
performing illumination correction on the noise-reduced image to obtain a corrected image;
carrying out edge detection on the corrected image to obtain an edge detection image;
removing isolated noise points from the edge detection image to obtain a noise point removed image;
and performing feature extraction on the noise point removed image to obtain feature data of the noise point removed image.
In one embodiment, the graying the defect image to obtain a grayed image includes:
and performing graying processing on the defect image by using a weighted average method to obtain a grayed image.
In one embodiment, the performing noise reduction processing on the grayed image to obtain a noise-reduced image includes:
dividing the gray-scale image into N blocks with equal areas;
and respectively performing wavelet denoising processing on each block.
In another embodiment, the performing noise reduction processing on the grayed image to obtain a noise-reduced image includes: and performing noise reduction processing on the gray images by using a median filtering function to obtain noise-reduced images.
In one embodiment, performing illumination correction on the noise-reduced image to obtain a corrected image includes:
and adjusting the brightness of the noise-reduced image by using the following formula to obtain a brightness-adjusted image:
Figure BDA0002342267690000021
in the formula, e1, e2, e3 and e4 are all preset constant parameters, and ld is a global segmentation threshold obtained by Otsu; f (x, y) represents the gray value of the pixel point at the (x, y) position in the noise reduction image, af (x, y) represents the gray value of the pixel point at the (x, y) position after the brightness adjustment, and af represents the brightness adjustment image;
and carrying out highlight and shade suppression on the brightness adjustment image by using the following formula to obtain a corrected image:
Figure BDA0002342267690000031
after the highlight and shade pressing is carried out, the aft (x, y) represents the gray value of the pixel point at the (x, y) position, the aft represents the correction image, the aveL represents the average value of the gray values of all the pixel points in the brightness adjustment image, and the gx represents the pressing coefficient.
According to the embodiment of the invention, the condition of unbalanced illumination in the image can be effectively avoided by suppressing the high brightness and the dark of the image, and the accuracy of subsequent processing is improved. The global segmentation threshold obtained by Otsu is used in the processing, so that the brightness adjustment is more accurate.
In another embodiment, gamma correction is used to perform illumination correction on the noise-reduced image, resulting in a corrected image.
In one embodiment, performing edge detection on the corrected image to obtain an edge-detected image includes:
carrying out corrosion operation and expansion operation on the corrected image to obtain a corrosion image FSP and an expansion image PZP;
obtaining the gray level change peak toph (x, y) of each pixel point in the corrected image aft:
toph(x,y)＝th1×[aft(x,y)-FSP(x,y)]+th2×[aft(x,y)-PZP(x,y)]，
th1 and th2 are edge detection weight parameters, FSP (x, y) represents the gray-scale value at (x, y) in the erosion image, PZP (x, y) represents the gray-scale value at (x, y) in the dilation image;
obtaining the identifiability parameter KSP (x, y) of each pixel point in the corrected image aft:
Figure BDA0002342267690000032
in the formula, g1, g2 and g3 are all preset edge detection parameters, and Γ 1 and Γ 2 respectively represent a highlight threshold and a shade threshold in aft; FCZ represents the mean of the gray values of all the pixels in the aft.
And judging whether toph (x, y) > KSP (x, y) is satisfied or not for the pixel point at (x, y) in the corrected image aft, if so, taking the pixel point at (x, y) as an edge pixel point, and marking the edge pixel point.
According to the embodiment of the invention, whether the pixel point belongs to the edge pixel point is detected through the gray scale change peak value and the identifiability parameter, and the highlight threshold value and the shade threshold value are considered during detection, so that the edge point is detected more accurately.
In one embodiment, the performing wavelet denoising processing on each block respectively includes:
for the nth block, the maximum gray difference value maxC of the pixel points in the block is calculatedn，maxHCn＝maxn-minn，n∈[1,N],maxnAnd minnRespectively representing the maximum value and the minimum value of the gray value of the pixel point in the nth block if maxCnIf the threshold value is less than the preset threshold value hdThre, the wavelet denoising processing is not carried out on the block;
otherwise, the nth block is subjected to the following filtering processing:
wavelet decomposition is carried out on the block, and high-frequency coefficient images HFC of the block are respectively obtainedvarAnd a low frequency coefficient image LFC;
for high frequency coefficient image HFCvarThe following processes are performed:
Figure BDA0002342267690000041
in the formula, bl is epsilon [ HL, LH, HH ∈ [ ]]HL, LH, HH represent three high frequency subband images in wavelet transform, aHFC, respectivelyblA high-frequency coefficient image after the processing, and (x, y) a high-frequency coefficient image HFCblThe positions of the middle pixel points yza and yzb respectively represent a preset high-frequency decomposition first threshold value and a high-frequency decomposition second threshold value, and sf represents a step function; aHFCbl(x, y) represents the gray value of the pixel point at the position (x, y) in the processed high-frequency coefficient image; HFCbl(x, y) represents the gray value of the pixel point at (x, y) in the high-frequency coefficient image;
and for the low-frequency coefficient image, the following processing is carried out:
Figure BDA0002342267690000042
in the formula, aLFC represents the processed low-frequency coefficient image, α and β represent preset weight parameters, α + β is 1, B (x, y) represents a set of pixels in the neighborhood of (x, y) of the pixel in the low-frequency coefficient image, wherein fw is multiplied by fw, j is the element of the set and represents the position of the pixel in the neighborhood, ntol is the element of the setx,yA total number of pixel points representing a neighborhood of pixel points at (x, y) in the low frequency coefficient image,
Figure BDA0002342267690000055
expressing the standard deviation of the gray values of all the pixel points in the neighborhood; GZ represents a preset adjustment parameter; PJx,yRepresenting the average value of the gray values of all the pixel points in the neighborhood; the gray value of a pixel point with the position (i, j) in the field of LFC (i, j);
Figure BDA0002342267690000051
in the formula, c and d are preset control parameters,
Figure BDA0002342267690000052
representing the scale parameters, COR (x, y) representing the adjustment function,
Figure BDA0002342267690000053
in the formula, ndx,yExpressing the number of pixel points in the neighborhood, which are larger than the gray value of the pixel point at the center of the neighborhood;
Figure BDA0002342267690000054
δHrepresenting a gaussian filter standard deviation;
performing secondary wavelet decomposition on the processed low-frequency coefficient image aLFC to obtain a secondary high-frequency coefficient image tHFCbl2，bl2∈[HL,LH,HH]Representing three high-frequency sub-band images obtained by secondary wavelet decomposition;
image of high frequency coefficient HFCvarAnd a quadratic high frequency coefficient image tHFCbl2And carrying out image reconstruction to obtain a noise reduction image.
According to the embodiment of the invention, by setting the self-defined threshold parameter and adopting the corresponding processing function for different high-frequency coefficient conditions according to the relationship between the gray value and the threshold, the problems of incomplete edge information and unclean noise removal in image reconstruction existing in the conventional soft threshold function are effectively solved, and the pixel points in the gray image are effectively removed. The low-frequency coefficient is processed through the scale parameters and the Gaussian filtering standard deviation, the influence of the neighborhood of the pixel points is considered, meanwhile, the gray average value and the standard deviation of the image are also considered, and the problem that the edge is fuzzy in the prior art is solved.
The invention provides a method for detecting concrete defects at the top of a concrete column member in an image detection mode, which effectively solves the problem of low efficiency in the traditional detection mode.
From the above description of embodiments, it is clear for a person skilled in the art that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For a hardware implementation, a processor may be implemented in one or more of the following units: an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For a software implementation, some or all of the procedures of an embodiment may be performed by a computer program instructing associated hardware. In practice, the program may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer readable media include computer storage media and communication media, where communication media
Including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. Computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (7)

1. A method for detecting concrete defects at the top of a concrete column member is characterized by comprising the following steps:
acquiring a defect image of concrete at the top of the concrete column member;
extracting the characteristics of the defect image to obtain the characteristic data of the defect image;
and determining the type of the defects existing in the concrete on the top of the concrete column member according to the characteristic data.
2. The method for detecting the concrete column member top concrete defect according to claim 1, wherein the extracting the feature of the defect image to obtain the feature data of the defect image comprises:
carrying out graying processing on the defect image to obtain a grayed image;
carrying out noise reduction processing on the gray images to obtain noise reduction images;
performing illumination correction on the noise-reduced image to obtain a corrected image;
carrying out edge detection on the corrected image to obtain an edge detection image;
removing isolated noise points from the edge detection image to obtain a noise point removed image;
and performing feature extraction on the noise point removed image to obtain feature data of the noise point removed image.
3. The method for detecting concrete column member top concrete defects according to claim 2, wherein the graying the defect image to obtain a grayed image comprises:
and performing graying processing on the defect image by using a weighted average method to obtain a grayed image.
4. The method for detecting concrete column member top concrete defects according to claim 2, wherein the denoising processing of the grayed image to obtain a denoising image comprises:
dividing the gray-scale image into N blocks with equal areas;
and respectively performing wavelet denoising processing on each block.
5. The method of claim 2, wherein the illumination correction of the noise-reduced image to obtain a corrected image comprises:
and adjusting the brightness of the noise-reduced image by using the following formula to obtain a brightness-adjusted image:
Figure FDA0002342267680000011
in the formula, e1, e2, e3 and e4 are all preset constant parameters, and ld is a global segmentation threshold obtained by Otsu; f (x, y) represents the gray value of the pixel point at the (x, y) position in the noise reduction image, af (x, y) represents the gray value of the pixel point at the (x, y) position after the brightness adjustment, and af represents the brightness adjustment image;
and carrying out highlight and shade suppression on the brightness adjustment image by using the following formula to obtain a corrected image:
Figure FDA0002342267680000021
after the highlight and shade pressing is carried out, the aft (x, y) represents the gray value of the pixel point at the (x, y) position, the aft represents the correction image, the aveL represents the average value of the gray values of all the pixel points in the brightness adjustment image, and the gx represents the pressing coefficient.
6. The method of claim 5, wherein performing edge detection on the corrected image to obtain an edge detection image comprises:
carrying out corrosion operation and expansion operation on the corrected image to obtain a corrosion image FSP and an expansion image PZP;
obtaining the gray level change peak toph (x, y) of each pixel point in the corrected image aft:
toph(x,y)＝th1×[aft(x,y)-FSP(x,y)]+th2×[aft(x,y)-PZP(x,y)]，
th1 and th2 are edge detection weight parameters, FSP (x, y) represents the gray-scale value at (x, y) in the erosion image, PZP (x, y) represents the gray-scale value at (x, y) in the dilation image;
obtaining the identifiability parameter KSP (x, y) of each pixel point in the corrected image aft:
Figure FDA0002342267680000022
in the formula, g1, g2 and g3 are all preset edge detection parameters, and Γ 1 and Γ 2 respectively represent a highlight threshold and a shade threshold in aft; FCZ represents the mean of the gray values of all the pixels in the aft.
And judging whether toph (x, y) > KSP (x, y) is satisfied or not for the pixel point at (x, y) in the corrected image aft, if so, taking the pixel point at (x, y) as an edge pixel point, and marking the edge pixel point.
7. The method for detecting concrete defects on the top of a concrete column member according to claim 4, wherein the wavelet denoising treatment is performed on each block respectively, and comprises the following steps:
for the nth block, the maximum gray level difference max C of the pixel points in the block is calculatedn，max HCn＝maxn-minn，n∈[1,N],maxnAnd minnRespectively representing the maximum value and the minimum value of the gray value of the pixel point in the nth block if maxCnIf the threshold value is less than the preset threshold value hdThre, the wavelet denoising processing is not carried out on the block;
otherwise, the nth block is subjected to the following filtering processing:
wavelet decomposition is carried out on the block, and high-frequency coefficient images HFC of the block are respectively obtainedvarAnd a low frequency coefficient image LFC;
for high frequency coefficient image HFCvarThe following processes are performed:
Figure FDA0002342267680000031
in the formula, bl is epsilon [ HL, LH, HH ∈ [ ]]HL, LH, HH represent three high frequency subband images in wavelet transform, aHFC, respectivelyblA high-frequency coefficient image after the processing, and (x, y) a high-frequency coefficient image HFCblThe positions of the middle pixel points yza and yzb respectively represent a preset high-frequency decomposition first threshold value and a high-frequency decomposition second threshold value, and sf represents a step function; aHFCbl(x,y)To representGray values of pixel points at (x, y) positions in the processed high-frequency coefficient image; HFCbl(x, y) represents the gray value of the pixel point at (x, y) in the high-frequency coefficient image;
and for the low-frequency coefficient image, the following processing is carried out:
Figure FDA0002342267680000032
in the formula, lfc represents a processed low-frequency coefficient image, α and β represent preset weight parameters, α + β is 1, and B (x, y) represents a pixel point in the neighborhood of fw × fw of a pixel point in (x, y) in the low-frequency coefficient image(ii), (i, j) being an element of said set, representing the position of a pixel point in said neighborhood; ntolx,yA total number of pixel points representing a neighborhood of pixel points at (x, y) in the low frequency coefficient image,
Figure FDA0002342267680000033
expressing the standard deviation of the gray values of all the pixel points in the neighborhood; GZ represents a preset adjustment parameter; PJx,yRepresenting the average value of the gray values of all the pixel points in the neighborhood; the gray value of a pixel point with the position (i, j) in the field of LFC (i, j);
Figure FDA0002342267680000041
in the formula, c and d are preset control parameters,
Figure FDA0002342267680000042
representing the scale parameters, COR (x, y) representing the adjustment function,
Figure FDA0002342267680000043
in the formula, ndx,yExpressing the number of pixel points in the neighborhood, which are larger than the gray value of the pixel point at the center of the neighborhood;
Figure FDA0002342267680000044
δHrepresenting a gaussian filter standard deviation;
performing secondary wavelet decomposition on the processed low-frequency coefficient image aLFC to obtain a secondary high-frequency coefficient image tHFCbl2，bl2∈[HL,LH,HH]Representing three high-frequency sub-band images obtained by secondary wavelet decomposition;
image of high frequency coefficient HFCvarAnd a quadratic high frequency coefficient image tHFCbl2And carrying out image reconstruction to obtain a noise reduction image.
CN201911381075.8A 2019-12-27 2019-12-27 Method for detecting top concrete defect of concrete column member Active CN111223074B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911381075.8A CN111223074B (en) 2019-12-27 2019-12-27 Method for detecting top concrete defect of concrete column member

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911381075.8A CN111223074B (en) 2019-12-27 2019-12-27 Method for detecting top concrete defect of concrete column member

Publications (2)

Publication Number Publication Date
CN111223074A true CN111223074A (en) 2020-06-02
CN111223074B CN111223074B (en) 2023-04-21

Family

ID=70832174

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911381075.8A Active CN111223074B (en) 2019-12-27 2019-12-27 Method for detecting top concrete defect of concrete column member

Country Status (1)

Country Link
CN (1) CN111223074B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115272174A (en) * 2022-06-15 2022-11-01 武汉市市政路桥有限公司 Municipal road detection method and system

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040008904A1 (en) * 2003-07-10 2004-01-15 Samsung Electronics Co., Ltd. Method and apparatus for noise reduction using discrete wavelet transform
CN101691994A (en) * 2009-09-30 2010-04-07 浙江大学 Method for automatically positioning and detecting maximum width of tunnel crack
CN107169953A (en) * 2017-04-07 2017-09-15 西安电子科技大学 Bridge concrete surface crack detection method based on HOG features
CN108548868A (en) * 2018-03-01 2018-09-18 上海交通大学 Steel-shelled concrete fault of construction detection method, system and device and storage medium
CN108961230A (en) * 2018-06-28 2018-12-07 武汉大学 The identification and extracting method of body structure surface FRACTURE CHARACTERISTICS
CN109682316A (en) * 2018-11-19 2019-04-26 湖北电鹰科技有限公司 Distress in concrete recognition methods and system based on unmanned plane imaging
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
CN110514663A (en) * 2019-08-19 2019-11-29 上海市建筑科学研究院 A kind of detection method of concrete column component top concrete defect

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040008904A1 (en) * 2003-07-10 2004-01-15 Samsung Electronics Co., Ltd. Method and apparatus for noise reduction using discrete wavelet transform
CN101691994A (en) * 2009-09-30 2010-04-07 浙江大学 Method for automatically positioning and detecting maximum width of tunnel crack
CN107169953A (en) * 2017-04-07 2017-09-15 西安电子科技大学 Bridge concrete surface crack detection method based on HOG features
CN108548868A (en) * 2018-03-01 2018-09-18 上海交通大学 Steel-shelled concrete fault of construction detection method, system and device and storage medium
CN108961230A (en) * 2018-06-28 2018-12-07 武汉大学 The identification and extracting method of body structure surface FRACTURE CHARACTERISTICS
CN109682316A (en) * 2018-11-19 2019-04-26 湖北电鹰科技有限公司 Distress in concrete recognition methods and system based on unmanned plane imaging
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
CN110514663A (en) * 2019-08-19 2019-11-29 上海市建筑科学研究院 A kind of detection method of concrete column component top concrete defect

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115272174A (en) * 2022-06-15 2022-11-01 武汉市市政路桥有限公司 Municipal road detection method and system

Also Published As

Publication number Publication date
CN111223074B (en) 2023-04-21

Similar Documents

Publication Publication Date Title
CN107507173B (en) No-reference definition evaluation method and system for full-slice image
CN109242791B (en) Batch repair method for damaged plant leaves
KR101674078B1 (en) Method and apparatus for block-based image denoising
CN107230208B (en) Image noise intensity estimation method of Gaussian noise
CN109584240B (en) Landslide trailing edge crack displacement image identification method
CN102479383B (en) Method and device for removing salt and pepper noise
CN105243649A (en) Image denoising method based on secondary noise point detection
CN110796615B (en) Image denoising method, device and storage medium
CN116309559B (en) Intelligent identification method for production flaws of medium borosilicate glass
CN115984148B (en) Denoising enhancement method for high-throughput gene sequencing data
CN108470343A (en) A kind of improved method for detecting image edge
CN112561804A (en) Low-illumination underwater image enhancement method based on multi-scale detail enhancement
CN102982542A (en) Fundus image vascular segmentation method based on phase congruency
CN108133462B (en) Single image restoration method based on gradient field region segmentation
CN117058147B (en) Environment-friendly plastic product defect detection method based on computer vision
CN113191979B (en) Non-local mean denoising method for partitioned SAR (synthetic aperture radar) image
CN111008563B (en) Dim light scene seed germination detection method and device and readable storage medium
CN116664457B (en) Image processing method for enhancing denoising
CN116630321B (en) Intelligent bridge health monitoring system based on artificial intelligence
CN112053302B (en) Denoising method and device for hyperspectral image and storage medium
CN111028214A (en) Skin detection device based on cloud platform
CN110942427A (en) Image noise reduction method and device, equipment and storage medium
CN111223074A (en) Method for detecting concrete defects at top of concrete column member
CN117314766B (en) Method and system for enhancing surface image of toughened glass film of mobile phone
KR101651889B1 (en) Video quality enhancement device and method for extremely low-light video

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
CB02 Change of applicant information

Address after: 750000 No. 35 Jimin East Road, Yinchuan Economic and Technological Development Zone, Ningxia Hui Autonomous Region

Applicant after: Ningxia Construction Science Research Institute Group Co.,Ltd.

Address before: 750000 No. 35 Jimin East Road, Yinchuan Economic and Technological Development Zone, Ningxia Hui Autonomous Region

Applicant before: NINGXIA INSTITUTE OF BUILDING RESEARCH CO.,LTD.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant