CN115272174B - Municipal road detection method and system - Google Patents
Municipal road detection method and system Download PDFInfo
- Publication number
- CN115272174B CN115272174B CN202210675220.9A CN202210675220A CN115272174B CN 115272174 B CN115272174 B CN 115272174B CN 202210675220 A CN202210675220 A CN 202210675220A CN 115272174 B CN115272174 B CN 115272174B
- Authority
- CN
- China
- Prior art keywords
- image
- noise reduction
- target image
- pixel
- treatment
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 53
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000012216 screening Methods 0.000 claims abstract description 21
- 230000001537 neural effect Effects 0.000 claims abstract description 7
- 230000012010 growth Effects 0.000 claims description 29
- 230000035040 seed growth Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000007547 defect Effects 0.000 abstract description 10
- 238000000354 decomposition reaction Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000011946 reduction process Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
- G06T7/187—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
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a municipal road detection method, which comprises the following steps: s1, acquiring a surface image of a municipal road; s2, carrying out graying treatment on the surface image to obtain a graying image; s3, performing self-adaptive region growing treatment on the gray image to obtain a plurality of subareas; s4, screening the sub-areas according to a set screening rule to obtain a plurality of target images; s5, performing noise reduction processing on each target image by using a self-adaptive noise reduction algorithm to obtain a noise-reduced target image; s6, inputting the target image after noise reduction into a convolutional neural model which is trained in advance for detection, and obtaining a detection result. The invention also discloses a system for realizing the method. The invention effectively reduces the number of the pixel points entering the noise reduction processing step, thereby effectively improving the efficiency of defect detection of the municipal road by using machine vision.
Description
Technical Field
The invention relates to the field of road detection, in particular to a municipal road detection method and system.
Background
Road detection is an important component of municipal road maintenance work. The traditional road detection is generally carried out in a manual mode, but the visual detection efficiency of human eyes is relatively low, so that defects such as cracks and pits in the road are not easy to discover in time. With the development of technology, a way to detect a road by machine vision is now emerging. Compared with the traditional visual detection of human eyes, the machine vision detection mode enables the efficiency of detecting the municipal roads to be improved remarkably. In the existing machine vision detection mode, in the noise reduction process of the road image, the noise reduction processing is carried out on the whole image by adopting a single noise reduction mode, so that the number of pixel points needing noise reduction is excessive, and the efficiency of defect detection on the municipal road by using machine vision is reduced.
Disclosure of Invention
The invention aims to disclose a municipal road detection method, which solves the problems that in the prior art, in the process of denoising a road image, a single denoising mode is adopted to perform denoising treatment on the whole image, so that the number of pixel points required to be denoised is excessive, and the efficiency of detecting defects of the municipal road by using machine vision is reduced.
In order to achieve the above purpose, the invention adopts the following technical scheme:
in one aspect, the present invention provides a method for detecting a municipal road, comprising:
s1, acquiring a surface image of a municipal road;
s2, carrying out graying treatment on the surface image to obtain a graying image;
s3, performing self-adaptive region growing treatment on the gray image to obtain a plurality of subareas;
s4, screening the sub-areas according to a set screening rule to obtain a plurality of target images;
s5, performing noise reduction processing on each target image by using a self-adaptive noise reduction algorithm to obtain a noise-reduced target image;
s6, inputting the target image after noise reduction into a convolutional neural model which is trained in advance for detection, and obtaining a detection result.
Preferably, the S2 includes:
graying treatment is carried out on the surface image by adopting the following formula:
Gray(x,y)＝w 1 ×R(x,y)+w 2 ×G(x,y)+w 3 ×B(x,y)
wherein Gray represents a graying image, (x, y) represents coordinates of a pixel point, gray (x, y) represents a pixel value of a pixel point having coordinates of (x, y) in the graying image, and w 1 、w 2 、w 3 The preset calculation coefficients are represented, R (x, y), G (x, y) and B (x, y) represent pixel values of pixel points with coordinates (x, y) in the image R, the image G and the image B respectively, and R, G, B represent images corresponding to red components, green components and blue components of the surface image in an RGB color space respectively.
Preferably, the S3 includes:
calculating the occurrence frequency of each pixel value in the gray-scale image respectively;
for the ith pixel value, if its corresponding frequency freq i If the pixel value is smaller than the preset frequency threshold value, the ith pixel value is stored into a set setwtbr to be grown, i epsilon [1, N]N represents the total number of types of pixel values in the greyscale image;
and respectively carrying out seed growth treatment on the pixel points corresponding to each pixel value in setwtbr to obtain a plurality of subareas.
Preferably, the seed growth processing is performed on the pixel point corresponding to each pixel value in setwtbr to obtain a plurality of sub-regions, including:
sorting pixel values in setwtbr from small to large to obtain an ordered set setwtbr';
seed growth treatment 1:
storing all pixel points corresponding to the 1 st element in the ordered set setwtbr' into a set wtgr 1 ；
Respectively by wtgr 1 Each pixel point in the array is used as a seed to perform image area growth processing to obtain a plurality of sub-pixelsA region;
will aggregate wtgr 1 The pixel points of all the subareas obtained by the area growth processing are stored in a collection setalu;
treatment of the kth seed growth:
storing all pixel points corresponding to the kth element in the ordered set setwtbr' into a set wtgr k ；
Will aggregate wtgr k Pixel point corresponding to intersection of set setalu from set wtgr k Is deleted to obtain the set wtgr k '；
Respectively by wtgr k Each pixel point in' is used as a seed, and image area growth processing is carried out to obtain a plurality of subareas;
will aggregate wtgr k The pixel points in the' are subjected to region growing treatment, and the pixel points of all the subareas obtained by the region growing treatment are stored in a collection setalu;
where k ε [2, M ], M represents the total number of elements contained in setwtbr.
Preferably, the S4 includes:
storing the subareas with the area occupation ratio larger than a preset occupation ratio threshold value into a set H;
and respectively acquiring the corresponding minimum circumscribed rectangle of each sub-region in the set H, and taking the pixel points in the range of the minimum circumscribed rectangle as the pixel points of the target image corresponding to the sub-region.
Preferably, the area ratio is calculated by the following formula:
where areat represents the area ratio of the sub-region, numofblokc represents the number of pixels contained in the sub-region, and numofGray represents the number of pixels contained in the grayscale image.
Preferably, the S5 includes:
for the target image P, calculating a pixel value discrete coefficient dispcoef of the target image P P ；
Based on discoef P An algorithm for noise reduction processing of the target image P is selected.
Preferably, the pixel value discrete coefficient dispcoef P The calculation is performed by the following formula:
wherein alpha and beta represent preset proportional coefficients, setP represents a set of pixel points in the target image P, and Gray u The pixel value representing the pixel point u in setP, numfsetP representing the total number of elements contained in setP, stdev representing a preset pixel value variance standard value, numfedg representing the total number of edge pixel points in the target image P.
Preferably, the said discoef-based P An algorithm for performing noise reduction processing on a target image P is selected, comprising:
if discoef P If the difference is larger than the preset discrete coefficient threshold value, adopting an improved wavelet noise reduction algorithm to perform noise reduction treatment on the target image P, and obtaining a noise-reduced target image;
if discoef P And if the value is smaller than or equal to a preset discrete coefficient threshold value, adopting a median filter to perform noise reduction treatment on the target image P, and obtaining the target image after noise reduction.
On the other hand, the invention also provides a municipal road detection system, which comprises a shooting module, a graying module, a seed growth module, a screening module, a noise reduction module and a detection module;
the shooting module is used for acquiring a surface image of the municipal road;
the graying module is used for carrying out graying treatment on the surface image to obtain a graying image;
the seed growth module is used for carrying out self-adaptive region growth treatment on the gray-scale image to obtain a plurality of subareas;
the screening module is used for screening the sub-areas according to the set screening rules to obtain a plurality of target images;
the noise reduction module is used for carrying out noise reduction processing on each target image by using a self-adaptive noise reduction algorithm to obtain a noise-reduced target image;
the detection module is used for inputting the target image after noise reduction into a convolutional neural model which is trained in advance for detection, and a detection result is obtained.
In the process of processing the surface image of the municipal road, the invention firstly grey-scales, then carries out self-adaptive region growth processing on the image obtained by grey-scales to obtain a plurality of subareas, obtains a plurality of target images by the subareas, then carries out noise reduction processing on the target images, and finally carries out road defect detection based on the target images after the noise reduction processing. The invention effectively reduces the number of the pixel points entering the noise reduction processing step, thereby effectively improving the efficiency of defect detection of the municipal road by using machine vision.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the invention, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings.
Fig. 1 is a diagram illustrating an exemplary embodiment of a method for detecting a town road according to the present invention.
FIG. 2 is a diagram illustrating an exemplary embodiment of a town road detection system according to the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
In one aspect, as shown in an embodiment of fig. 1, the present invention provides a method for detecting a town road, comprising:
s1, acquiring a surface image of a municipal road;
s2, carrying out graying treatment on the surface image to obtain a graying image;
s3, performing self-adaptive region growing treatment on the gray image to obtain a plurality of subareas;
s4, screening the sub-areas according to a set screening rule to obtain a plurality of target images;
s5, performing noise reduction processing on each target image by using a self-adaptive noise reduction algorithm to obtain a noise-reduced target image;
s6, inputting the target image after noise reduction into a convolutional neural model which is trained in advance for detection, and obtaining a detection result.
In the process of processing the surface image of the municipal road, the invention firstly grey-scales, then carries out self-adaptive region growth processing on the image obtained by grey-scales to obtain a plurality of subareas, obtains a plurality of target images by the subareas, then carries out noise reduction processing on the target images, and finally carries out road defect detection based on the target images after the noise reduction processing. The invention effectively reduces the number of the pixel points entering the noise reduction processing step, thereby effectively improving the efficiency of defect detection of the municipal road by using machine vision.
Preferably, the S2 includes:
graying treatment is carried out on the surface image by adopting the following formula:
Gray(x,y)＝w 1 ×R(x,y)+w 2 ×G(x,y)+w 3 ×B(x,y)
wherein Gray represents a graying image, (x, y) represents coordinates of a pixel point, gray (x, y) represents a pixel value of a pixel point having coordinates of (x, y) in the graying image, and w 1 、w 2 、w 3 The preset calculation coefficients are represented, R (x, y), G (x, y) and B (x, y) represent pixel values of pixel points with coordinates (x, y) in the image R, the image G and the image B respectively, and R, G, B represent images corresponding to red components, green components and blue components of the surface image in an RGB color space respectively.
Further, w 1 ∈[0.29，031]，w 2 ∈[0.58,0.61]，w 3 ∈[0.09,0.12]。
Preferably, the S3 includes:
calculating the occurrence frequency of each pixel value in the gray-scale image respectively;
for the ith pixel value, if its corresponding frequency freq i If the pixel value is smaller than the preset frequency threshold value, the ith pixel value is stored into a set setwtbr to be grown, i epsilon [1, N]N represents the total number of types of pixel values in the greyscale image;
and respectively carrying out seed growth treatment on the pixel points corresponding to each pixel value in setwtbr to obtain a plurality of subareas.
Conventional region growing algorithms, in which the pixels used as seeds are generally considered to be selected, are obviously not in accordance with the requirements of the present invention. Therefore, the invention improves the area growth algorithm, screens the pixel points serving as seeds through the frequency of the pixel values, and realizes the automatic acquisition of the seed pixel points. In the process of obtaining, the method discards the pixel value with overlarge frequency, thereby effectively compressing the number of seed pixel points and being beneficial to improving the operation speed. The larger the frequency is, the larger the probability that the pixel point is taken as the pixel point of the normal road surface area is, and the object of the invention is to detect the defect, so the pixel point of the defect area can be effectively obtained as the seed by setting the frequency threshold value.
Further, the frequency of occurrence of the pixel value is equal to the total number of pixel points corresponding to the pixel value divided by the total number of pixel points in the grayscale image.
Preferably, the seed growth processing is performed on the pixel point corresponding to each pixel value in setwtbr to obtain a plurality of sub-regions, including:
sorting pixel values in setwtbr from small to large to obtain an ordered set setwtbr';
seed growth treatment 1:
storing all pixel points corresponding to the 1 st element in the ordered set setwtbr' into a set wtgr 1 ；
Respectively by wtgr 1 Each pixel point in the array is used as a seed, and image area growth processing is carried out to obtain a plurality of sub-areas;
will aggregate wtgr 1 The pixel points of all the subareas obtained by the area growth processing are stored in a collection setalu;
treatment of the kth seed growth:
storing all pixel points corresponding to the kth element in the ordered set setwtbr' into a set wtgr k ；
Will aggregate wtgr k Pixel point corresponding to intersection of set setalu from set wtgr k The set wtgr 'is obtained by deletion of' k ；
Respectively as wtgr' k Each pixel point in the array is used as a seed, and image area growth processing is carried out to obtain a plurality of sub-areas;
will aggregate wtgr' k The pixel points of all the subareas obtained by the area growth processing are stored in a collection setalu;
where k ε [2, M ], M represents the total number of elements contained in setwtbr.
In the process of seed growth, the invention firstly carries out region growth from the pixel point corresponding to the minimum pixel value, and because the pixel value of noise is generally larger, the invention can reduce the influence of noise on seed growth, and in the process of region growth, the invention continuously stores all the pixel points belonging to the growth region as a set setalu, thus, along with the seed
The number of pixels that have been selected as growth areas is increasing, wtgr 'with increasing pixel values of the sub-pixels' k The number of pixels in (b) and wtgr k The difference of the number of the pixels is larger and larger, so that the number of the seed pixels entering the current growth treatment is effectively inhibited, and the growth speed of the region is effectively improved.
Preferably, in the process of performing the region growth, it is determined whether the growth condition is satisfied in the following manner:
for the pixel points setpixel serving as seeds, storing the pixel points in the neighborhood of the pixel points into a set setZ;
for pixel point z in setZ, a coefficient of difference between setpixel and z is calculated:
difid seedpixel,z ＝Φ×|Gray seedpixel -Gray z |+(1-Φ)×|neiT seedpixel -neiT z |
in the formula, difid seedpixel,z Represents the coefficient of difference between setpixel and z, Φ represents the duty control parameter, Φ ε (0, 1), gray seedpixel And Gray z Pixel values, neiT, representing seedpixel and z, respectively seedpixel Gradient magnitude mean, neiT, representing 8 neighborhoods of setpixel z Representing the gradient magnitude average of the 8 neighborhood of z;
if the difference coefficient is smaller than the set difference coefficient threshold, the pixel point z meets the growth condition, and if the difference coefficient is larger than or equal to the set difference coefficient threshold, the pixel point z does not meet the growth condition.
The existing growth condition judgment is generally only to judge the difference between pixel values, but the image obtained after the region growth is easy to have more holes only by the pixel values, so the invention also adds the parameter of gradient amplitude, realizes the effective inhibition of the holes and improves the accuracy of the result of the region growth.
Preferably, the S4 includes:
storing the subareas with the area occupation ratio larger than a preset occupation ratio threshold value into a set H;
and respectively acquiring the corresponding minimum circumscribed rectangle of each sub-region in the set H, and taking the pixel points in the range of the minimum circumscribed rectangle as the pixel points of the target image corresponding to the sub-region.
Specifically, because the sub-region after the region growing process may only include the foreground pixel point, when the pixel point of the edge region is subjected to the noise reduction process, the pixel point of the edge region is lack of the reference pixel point, and the noise reduction process cannot be performed on the pixel point of the edge region, the invention effectively solves the problem by acquiring the minimum circumscribed rectangle. Because the noise pixels in the image always exist singly or exist in a small area, partial noise pixels can be removed in advance through screening of the area occupation ratio, and the number of the pixels participating in noise reduction of the subsequent image is reduced.
Preferably, the area ratio is calculated by the following formula:
where areat represents the area ratio of the sub-region, numofblokc represents the number of pixels contained in the sub-region, and numofGray represents the number of pixels contained in the grayscale image.
Preferably, the S5 includes:
for the target image P, calculating a pixel value discrete coefficient dispcoef of the target image P P ；
Based on discoef P An algorithm for noise reduction processing of the target image P is selected.
The existing noise reduction processing mode generally uses the same noise reduction mode to perform noise reduction processing on all pixel points in the gray image, however, the noise reduction mode does not consider the distribution of pixel values, and the same noise reduction processing mode is used, so that if the noise reduction processing process is complex, the time required for noise reduction is long, and if the noise reduction processing process is simple, the noise reduction effect is poor. Therefore, after the target image is obtained, the noise reduction processing mode is obtained through the pixel value discrete coefficient, and the balance between the noise reduction effect and the noise reduction speed is realized.
Preferably, the pixel value discrete coefficient dispcoef P The calculation is performed by the following formula:
wherein alpha and beta represent preset proportional coefficients, setP represents a set of pixel points in the target image P, and Gray u The pixel value representing the pixel point u in setP, numfsetP representing the total number of elements contained in setP, stdev representing a preset pixel value variance standard value, numfedg representing the total number of edge pixel points in the target image P.
When the pixel value discrete coefficient is calculated, the pixel value discrete coefficient is calculated from the difference of the pixel values and the difference of the edge pixel points, so that the pixel value discrete coefficient can more accurately represent the distribution condition of the pixel values among the pixel points in the target image.
Preferably, the said discoef-based P An algorithm for performing noise reduction processing on a target image P is selected, comprising:
if discoef P If the difference is larger than the preset discrete coefficient threshold value, adopting an improved wavelet noise reduction algorithm to perform noise reduction treatment on the target image P, and obtaining a noise-reduced target image;
if discoef P And if the value is smaller than or equal to a preset discrete coefficient threshold value, adopting a median filter to perform noise reduction treatment on the target image P, and obtaining the target image after noise reduction.
The larger the difference between the pixel points is, the more the number of the edge pixel points is, the more unbalanced the pixel value distribution is, the larger the pixel value discrete coefficient is, the more complex noise reduction algorithm is needed to be used for noise reduction to ensure the noise reduction effect, otherwise, the more balanced the pixel value distribution is, and the simpler algorithm with higher noise reduction speed is used for noise reduction to improve the noise reduction speed.
Preferably, the noise reduction processing is performed on the target image P by using an improved wavelet noise reduction algorithm, so as to obtain a noise reduced target image, including:
d-layer wavelet decomposition is carried out on the target image to obtain a plurality of wavelet high-frequency coefficients and 1 wavelet low-frequency coefficient;
each wavelet high-frequency coefficient is processed as follows to obtain a wavelet high-frequency coefficient after noise reduction:
if |smwafr d,c |≥thrsd d,c The wavelet high frequency coefficients are calculated using the following formula:
if |smwafr d,c |＜thrsd d,c Then adoptThe wavelet high frequency coefficients are calculated using the following formula:
afsmwafr d,c ＝0
in the formula, smwafr d,c Represents the c-th wavelet high-frequency coefficient obtained by d-th wavelet decomposition, c E [1,3 ]]，afsmwafr d,c Representation of smwafr d,c The wavelet high-frequency coefficient obtained after noise reduction, delta represents a preset first control coefficient, delta is more than 0,
representing a preset second control factor, +.>
thrsd d,c An adaptive threshold value representing the c-th wavelet high frequency coefficient obtained by d-th wavelet decomposition hfn represents a judgment function, if smwafr d,c Above 0, hfn (smwafr) d,c ) The value of (1) is smwafr d,c Less than 0, hfn (smwafr) d,c ) The value of (2) is-1, if smwafr d,c Equal to 0, then hfn (smwafr d,c ) The value of (2) is 0; d E [1, D]；
And carrying out wavelet reconstruction on the wavelet low-frequency coefficient and the wavelet high-frequency coefficient after noise reduction to obtain a target image after noise reduction.
When the noise reduction processing is performed, the noise reduction processing is performed on the wavelet high-frequency coefficients under different conditions through the self-adaptive threshold value, so that the pertinence of a noise reduction processing function is improved, and the accuracy of the noise reduction effect is further improved. The setting mode of the noise reduction processing function can avoid the problem that the noise reduction effect is deviated due to the fact that the traditional threshold value has a breakpoint. Compared with the hard threshold, when the wavelet high-frequency coefficient is smaller, the adaptive threshold value obtained by the method is continuous, and the occurrence of break points is avoided.
Preferably, the adaptive threshold value is calculated using the following formula:
in thrsd d,c Adaptive threshold value representing the c-th wavelet high frequency coefficient obtained by d-th wavelet decomposition zm d Represents the maximum value, am, of the wavelet high frequency coefficient obtained by the wavelet classification of the d layer d Representing the minimum value of the wavelet high frequency coefficients obtained by the wavelet classification of the d layer lm d Representing the intermediate value of the wavelet high-frequency coefficient obtained by the wavelet classification of the d-th layer, and Ω represents a preset constant coefficient.
The threshold value is related to each wavelet high-frequency coefficient obtained by the same layer of wavelet decomposition, and the adaptability of the obtained threshold value is improved by setting the maximum value, the intermediate value and the minimum value to be equal to parameters directly related to wavelet decomposition results.
On the other hand, as shown in an embodiment of fig. 2, the invention also provides a municipal road detection system, which comprises a shooting module, a graying module, a seed growing module, a screening module, a noise reduction module and a detection module;
the shooting module is used for acquiring a surface image of the municipal road;
the graying module is used for carrying out graying treatment on the surface image to obtain a graying image;
the seed growth module is used for carrying out self-adaptive region growth treatment on the gray-scale image to obtain a plurality of subareas;
the screening module is used for screening the sub-areas according to the set screening rules to obtain a plurality of target images;
the noise reduction module is used for carrying out noise reduction processing on each target image by using a self-adaptive noise reduction algorithm to obtain a noise-reduced target image;
the detection module is used for inputting the target image after noise reduction into a convolutional neural model which is trained in advance for detection, and a detection result is obtained.
While embodiments of the invention have been shown and described, it will be understood by those skilled in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
It should be noted that, in each embodiment of the present invention, each functional unit/module may be integrated in one processing unit/module, or each unit/module may exist alone physically, or two or more units/modules may be integrated in one unit/module. The integrated units/modules described above may be implemented either in hardware or in software functional units/modules.
From the description of the embodiments above, it will be apparent to those skilled in the art that the embodiments described herein may be implemented in hardware, software, firmware, middleware, code, or any suitable combination thereof. For a hardware implementation, the 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 flow of an embodiment may be accomplished by a computer program to instruct the associated hardware.
When implemented, the above-described programs may be stored in or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and 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. The computer readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media 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.
Claims (6)
1. A method of municipal road detection, comprising:
s1, acquiring a surface image of a municipal road;
s2, carrying out graying treatment on the surface image to obtain a graying image;
s3, performing self-adaptive region growing treatment on the gray image to obtain a plurality of subareas;
s4, screening the sub-areas according to a set screening rule to obtain a plurality of target images;
s5, performing noise reduction processing on each target image by using a self-adaptive noise reduction algorithm to obtain a noise-reduced target image;
s6, inputting the target image after noise reduction into a convolutional neural model which is trained in advance for detection, and obtaining a detection result;
the step S3 comprises the following steps:
calculating the occurrence frequency of each pixel value in the gray-scale image respectively;
for the ith pixel value, if its corresponding frequency freq i If the pixel value is smaller than the preset frequency threshold value, the ith pixel value is stored into a set setwtbr to be grown, i epsilon [1, N]N represents the total number of types of pixel values in the greyscale image;
respectively carrying out seed growth treatment on pixel points corresponding to each pixel value in setwtbr to obtain a plurality of subareas;
the step S5 comprises the following steps:
for the target image P, calculating a pixel value discrete coefficient dispcoef of the target image P P ；
Based on discoef P Selecting an algorithm for performing noise reduction processing on the target image P;
the pixel value discrete coefficient dispcoef P The calculation is performed by the following formula:
wherein alpha and beta represent preset proportional coefficients, setP representsSet of pixels in target image P, gray u Pixel values representing pixel points u in setP, numfsetP representing the total number of elements contained in setP, stdev representing a preset pixel value variance standard value, numfedg representing the total number of edge pixel points in the target image P;
said discoef-based P An algorithm for performing noise reduction processing on a target image P is selected, comprising:
if discoef P If the difference is larger than the preset discrete coefficient threshold value, adopting an improved wavelet noise reduction algorithm to perform noise reduction treatment on the target image P, and obtaining a noise-reduced target image;
if discoef P And if the value is smaller than or equal to a preset discrete coefficient threshold value, adopting a median filter to perform noise reduction treatment on the target image P, and obtaining the target image after noise reduction.
2. The method for detecting a municipal road according to claim 1, wherein S2 comprises:
graying treatment is carried out on the surface image by adopting the following formula:
Gray(x,y)＝w 1 ×R(x,y)+w 2 ×G(x,y)+w 3 ×B(x,y)
wherein Gray represents a graying image, (x, y) represents coordinates of a pixel point, gray (x, y) represents a pixel value of a pixel point having coordinates of (x, y) in the graying image, and w 1 、w 2 、w 3 The preset calculation coefficients are represented, R (x, y), G (x, y) and B (x, y) represent pixel values of pixel points with coordinates (x, y) in the image R, the image G and the image B respectively, and R, G, B represent images corresponding to red components, green components and blue components of the surface image in an RGB color space respectively.
3. The method for detecting a municipal road according to claim 1, wherein seed growth processing is performed on each pixel point corresponding to each pixel value in setwtbr to obtain a plurality of sub-regions, respectively, comprising:
sorting pixel values in setwtbr from small to large to obtain an ordered set setwtbr';
seed growth treatment 1:
storing all pixel points corresponding to the 1 st element in the ordered set setwtbr' into a set wtgr 1 ；
Respectively by wtgr 1 Each pixel point in the array is used as a seed, and image area growth processing is carried out to obtain a plurality of sub-areas;
will aggregate wtgr 1 The pixel points of all the subareas obtained by the area growth processing are stored in a collection setalu;
treatment of the kth seed growth:
storing all pixel points corresponding to the kth element in the ordered set setwtbr' into a set wtgr k ；
Will aggregate wtgr k Pixel point corresponding to intersection of set setalu from set wtgr k Is deleted to obtain the set wtgr k '；
Respectively by wtgr k Each pixel point in' is used as a seed, and image area growth processing is carried out to obtain a plurality of subareas;
will aggregate wtgr k The pixel points in the' are subjected to region growing treatment, and the pixel points of all the subareas obtained by the region growing treatment are stored in a collection setalu;
where k ε [2, M ], M represents the total number of elements contained in setwtbr.
4. The method for detecting a municipal road according to claim 1, wherein S4 comprises:
storing the subareas with the area occupation ratio larger than a preset occupation ratio threshold value into a set H;
and respectively acquiring the corresponding minimum circumscribed rectangle of each sub-region in the set H, and taking the pixel points in the range of the minimum circumscribed rectangle as the pixel points of the target image corresponding to the sub-region.
5. The method of claim 4, wherein the area ratio is calculated by the following formula:
where areat represents the area ratio of the sub-region, numofblokc represents the number of pixels contained in the sub-region, and numofGray represents the number of pixels contained in the grayscale image.
6. The municipal road detection system is characterized by comprising a shooting module, a graying module, a seed growth module, a screening module, a noise reduction module and a detection module;
the shooting module is used for acquiring a surface image of the municipal road;
the graying module is used for carrying out graying treatment on the surface image to obtain a graying image;
the seed growth module is used for carrying out self-adaptive region growth treatment on the gray-scale image to obtain a plurality of subareas;
the screening module is used for screening the sub-areas according to the set screening rules to obtain a plurality of target images;
the noise reduction module is used for carrying out noise reduction processing on each target image by using a self-adaptive noise reduction algorithm to obtain a noise-reduced target image;
the detection module is used for inputting the target image after noise reduction into a convolutional neural model which is trained in advance for detection, and obtaining a detection result;
the self-adaptive region growing process is carried out on the gray image to obtain a plurality of subareas, which comprises the following steps:
calculating the occurrence frequency of each pixel value in the gray-scale image respectively;
for the ith pixel value, if its corresponding frequency freq i If the pixel value is smaller than the preset frequency threshold value, the ith pixel value is stored into a set setwtbr to be grown, i epsilon [1, N]N represents the total number of types of pixel values in the greyscale image;
respectively carrying out seed growth treatment on pixel points corresponding to each pixel value in setwtbr to obtain a plurality of subareas;
the step S5 comprises the following steps:
for the target image P, calculating a pixel value discrete coefficient dispcoef of the target image P P ；
Based on discoef P Selecting an algorithm for performing noise reduction processing on the target image P;
the pixel value discrete coefficient dispcoef P The calculation is performed by the following formula:
wherein alpha and beta represent preset proportional coefficients, setP represents a set of pixel points in the target image P, and Gray u Pixel values representing pixel points u in setP, numfsetP representing the total number of elements contained in setP, stdev representing a preset pixel value variance standard value, numfedg representing the total number of edge pixel points in the target image P;
said discoef-based P An algorithm for performing noise reduction processing on a target image P is selected, comprising:
if discoef P If the difference is larger than the preset discrete coefficient threshold value, adopting an improved wavelet noise reduction algorithm to perform noise reduction treatment on the target image P, and obtaining a noise-reduced target image;
if discoef P And if the value is smaller than or equal to a preset discrete coefficient threshold value, adopting a median filter to perform noise reduction treatment on the target image P, and obtaining the target image after noise reduction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210675220.9A CN115272174B (en) | 2022-06-15 | 2022-06-15 | Municipal road detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210675220.9A CN115272174B (en) | 2022-06-15 | 2022-06-15 | Municipal road detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115272174A CN115272174A (en) | 2022-11-01 |
| CN115272174B true CN115272174B (en) | 2023-05-19 |
Family
ID=83762003
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210675220.9A Active CN115272174B (en) | 2022-06-15 | 2022-06-15 | Municipal road detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115272174B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115797473B (en) * | 2023-02-09 | 2023-04-18 | 国网山东省电力公司东营供电公司 | Concrete forming evaluation method for civil engineering |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112907460A (en) * | 2021-01-25 | 2021-06-04 | 宁波市鄞州区测绘院 | Remote sensing image enhancement method |
| CN113077486A (en) * | 2021-04-30 | 2021-07-06 | 深圳世源工程技术有限公司 | Method and system for monitoring vegetation coverage rate in mountainous area |
| CN113191985A (en) * | 2021-05-24 | 2021-07-30 | 北京美医医学技术研究院有限公司 | Intelligent freckle removing system based on infrared laser |
| CN113361532A (en) * | 2021-03-10 | 2021-09-07 | 江西理工大学 | Image identification method, system, storage medium, equipment, terminal and application |
| CN113450340A (en) * | 2021-07-13 | 2021-09-28 | 北京美医医学技术研究院有限公司 | Skin texture detecting system |
| CN114170674A (en) * | 2021-11-02 | 2022-03-11 | 天津工业大学 | Method for distinguishing personnel state in man-machine cooperation scene |
| CN114581374A (en) * | 2022-01-25 | 2022-06-03 | 深圳飞亮智能科技有限公司 | Electric vehicle driving assisting system based on artificial intelligence technology |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105404847B (en) * | 2014-09-16 | 2019-01-29 | 北京计算机技术及应用研究所 | A kind of residue real-time detection method |
| CN106446914A (en) * | 2016-09-28 | 2017-02-22 | 天津工业大学 | Road detection based on superpixels and convolution neural network |
| CN111223074B (en) * | 2019-12-27 | 2023-04-21 | 宁夏建筑科学研究院集团股份有限公司 | Method for detecting top concrete defect of concrete column member |
-
2022
- 2022-06-15 CN CN202210675220.9A patent/CN115272174B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112907460A (en) * | 2021-01-25 | 2021-06-04 | 宁波市鄞州区测绘院 | Remote sensing image enhancement method |
| CN113361532A (en) * | 2021-03-10 | 2021-09-07 | 江西理工大学 | Image identification method, system, storage medium, equipment, terminal and application |
| CN113077486A (en) * | 2021-04-30 | 2021-07-06 | 深圳世源工程技术有限公司 | Method and system for monitoring vegetation coverage rate in mountainous area |
| CN113191985A (en) * | 2021-05-24 | 2021-07-30 | 北京美医医学技术研究院有限公司 | Intelligent freckle removing system based on infrared laser |
| CN113450340A (en) * | 2021-07-13 | 2021-09-28 | 北京美医医学技术研究院有限公司 | Skin texture detecting system |
| CN114170674A (en) * | 2021-11-02 | 2022-03-11 | 天津工业大学 | Method for distinguishing personnel state in man-machine cooperation scene |
| CN114581374A (en) * | 2022-01-25 | 2022-06-03 | 深圳飞亮智能科技有限公司 | Electric vehicle driving assisting system based on artificial intelligence technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115272174A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107507173B (en) | No-reference definition evaluation method and system for full-slice image | |
| CN116703910B (en) | Intelligent detection method for quality of concrete prefabricated bottom plate | |
| WO2021114564A1 (en) | Enhancement method for low-contrast infrared image | |
| CN115272174B (en) | Municipal road detection method and system | |
| CN112561804A (en) | Low-illumination underwater image enhancement method based on multi-scale detail enhancement | |
| WO1987007741A1 (en) | Image processing method for the removal of spot defects and apparatus therefor | |
| CN113077486B (en) | Method and system for monitoring vegetation coverage rate in mountainous area | |
| CN116630813B (en) | Highway road surface construction quality intelligent detection system | |
| CN100367770C (en) | Method for removing isolated noise point in video | |
| CN115937186A (en) | Textile defect identification method and system | |
| CN112233037B (en) | Image enhancement system and method based on image segmentation | |
| CN108898561A (en) | A kind of defogging method, server and the system of the Misty Image containing sky areas | |
| CN108810314A (en) | Unordered error based on the enhancing of multi-grey image edge spreads digital halftoning method | |
| CN110930330B (en) | Image segmentation and region growth based salt and pepper noise reduction algorithm | |
| CN110766662B (en) | Forging surface crack detection method based on multi-scale and multi-layer feature learning | |
| CN115660994B (en) | Image enhancement method based on regional least square estimation | |
| CN115797234A (en) | Method for enhancing low-contrast two-dimensional code image recognition effect | |
| CN115880181A (en) | Method, device and terminal for enhancing image contrast | |
| JP3909604B2 (en) | Image processing apparatus and image processing method | |
| CN111583213B (en) | Image generation method based on deep learning and no-reference quality evaluation | |
| CN110647843B (en) | Face image processing method | |
| CN109886901B (en) | Night image enhancement method based on multi-channel decomposition | |
| CN111145193A (en) | Adaptive global threshold value binarization method | |
| CN117422656B (en) | Low-illumination fuzzy traffic image enhancement method, device, equipment and medium | |
| CN115578388B (en) | Data processing method for textile production |
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 |