CN113674270A - Tire pattern consistency detection system and method - Google Patents
Tire pattern consistency detection system and method Download PDFInfo
- Publication number
- CN113674270A CN113674270A CN202111029178.5A CN202111029178A CN113674270A CN 113674270 A CN113674270 A CN 113674270A CN 202111029178 A CN202111029178 A CN 202111029178A CN 113674270 A CN113674270 A CN 113674270A
- Authority
- CN
- China
- Prior art keywords
- tire
- image
- feature
- edge
- images
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 55
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 239000012535 impurity Substances 0.000 claims abstract description 10
- 238000010606 normalization Methods 0.000 claims description 13
- 230000000903 blocking effect Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 235000009508 confectionery Nutrition 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 5
- 238000009434 installation Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a tire pattern consistency detection system and a method thereof, wherein the system comprises an image acquisition module, a specific condition processing module and a similarity matching module, wherein the image acquisition module is used for synchronously acquiring at least two tire original images and performing impurity filtering processing on the tire original images to acquire at least two tire local images; the specific condition processing module is used for searching slope lines from at least two local images of the tire, fitting the slope lines, dividing the slope lines into a plurality of characteristic groups according to specific conditions to obtain characteristic lines, and dividing tire patterns in each edge image into a plurality of characteristic blocks according to characteristic information of the characteristic lines; the similarity matching module can rapidly and efficiently measure and calculate the similarity value of the images of two coaxial tires synchronously acquired by the motor vehicle, analyzes the consistency of the tire installation specifications of the same model and the wear texture state in use, and has strong practical significance for replacing the manual subjective detection mode of the quality characteristics of the motor vehicle tires.
Description
Technical Field
The invention belongs to the technical field of automobile tire detection, and particularly relates to a tire pattern consistency detection system and a method thereof.
Background
We know a method for automatically searching for the presence of defects on the surface of a tyre. In this method, a two-dimensional or three-dimensional image of a surface is first acquired with a sensor by means of industrial vision techniques. These images are then analyzed by automated means to locate any defects on the surface. To this end, the automated device analyzes one or more texture parameters of the image, with the aim of segmenting the image on the one hand, in other words dividing the image into regions in which the texture parameters are different; and on the other hand, the purpose of which is to classify the image, in other words to match the segmented image with a set of images in the reference image base, is to identify any defects.
The image is divided into regions with different texture parameters, for example but not exclusively consisting of: the image is divided into regions corresponding to smooth surfaces, regions corresponding to rough surfaces and regions corresponding to striated surfaces.
However, when a vehicle runs, after the tires are worn for a long time, the wear degrees of the surfaces of the two coaxial tires are different, the textures are also deviated, and certain potential safety hazards are brought to running.
Disclosure of Invention
The embodiment of the invention provides a system and a method for detecting the consistency of tire patterns, and aims to solve the problems that the existing tire has deviation of the patterns after long-term wear, the patterns are difficult to guarantee consistency, and whether the specification models and the wear patterns of two coaxial tires are consistent or not is detected.
In view of the above problems, the technical solution proposed by the present invention is:
a tire pattern uniformity detection system comprising:
the image acquisition module is used for acquiring at least two original images of the tire, and performing impurity filtering treatment on the original images of the tire to obtain at least two local images of the tire;
the specific condition processing module is used for searching slope lines from at least two local images of the tire, performing fitting processing, dividing the slope lines into a plurality of characteristic groups according to specific conditions to obtain characteristic lines, and dividing tire patterns in each edge image into a plurality of characteristic blocks according to characteristic information of the characteristic lines;
and the similarity matching module is used for receiving each feature block of at least two edge images for comparison, judging whether each feature block of the at least two edge images is matched or not and outputting a result.
As a preferred technical solution of the present invention, the image acquisition module includes:
an obtaining unit for obtaining at least two tire original images, and constructing at least two HOG images based on the at least two tire original images;
the normalization processing unit is used for performing normalization processing on each HOG image, removing gradient information lower than a preset threshold value in each HOG image, and counting the density of texture information of each cell unit in each HOG image;
a labeling processing unit, configured to label a plurality of connected regions of the cell unit texture information in each HOG image, and sequentially arrange the plurality of connected regions in each HOG image from large to small according to a label;
a scanning unit for scanning the plurality of connected regions in each HOG image column by column to determine tire left and right boundary positions;
and the clipping unit is used for clipping other texture information of each HOG image to obtain a tire local image.
As a preferred embodiment of the present invention, the specific condition processing module includes:
the edge extraction unit is used for converting each tire local image into an edge map by using the candy edge extraction, taking values of each point in each edge map and traversing, and simultaneously searching a slope line from each edge map;
the initial fitting unit is used for carrying out optimal fitting on the slope lines with the same slope in each edge image and reserving the optimal slope line;
the refitting unit is used for performing optimal fitting on the optimal slope line in each edge image and keeping the longest slope line;
the characteristic line processing unit is used for dividing the longest slope line in each edge graph into a plurality of characteristic groups according to specific conditions, and processing and fitting the longest slope line in each characteristic group to obtain a plurality of characteristic lines;
and the blocking unit is used for carrying out blocking processing on the tire patterns of each edge image by utilizing the characteristic information of the characteristic lines to obtain a plurality of characteristic blocks.
As a preferred embodiment of the present invention, the specific condition is specifically the longest slope line having a close position, a close slope, and a close length.
As a preferred embodiment of the present invention, the feature information of the feature line is specifically a stored feature angle, an x coordinate of a start point, an x coordinate of an end point, a length, a minimum start point, a maximum end point, the number of longest slope lines, and an average y of the start points.
As a preferred technical solution of the present invention, the similarity matching module includes:
the judging unit is used for comparing each feature block of at least two edge images, calculating the similarity between each feature block of at least two edge images, and judging whether each feature block of at least two edge images is matched according to the similarity;
and the output unit is used for outputting the matching result.
On the other hand, the embodiment of the invention also provides a method for detecting the tire pattern consistency, which comprises the following steps:
s1, obtaining at least two tire original images, and carrying out impurity filtering processing on the tire original images to obtain at least two tire local images;
s2, slope lines are searched from at least two tire local images and are subjected to fitting processing, the images are divided into a plurality of feature groups according to specific conditions to obtain feature lines, and tire patterns in each edge image are divided into a plurality of feature blocks according to feature information of the feature lines;
s3, receiving and comparing each feature block of at least two edge maps, judging whether each feature block of at least two edge maps is matched, and outputting a result.
As a preferred technical solution of the present invention, the obtaining of the tire original image and the obtaining of the tire local image by performing the impurity filtering process on the tire original image specifically comprise the steps of:
s11, obtaining at least two tire original images, and constructing at least two HOG images based on the at least two tire original images;
s12, performing normalization processing on each HOG image, removing gradient information lower than a preset threshold value in each HOG image, and counting the density of texture information of each cell unit in each HOG image;
s13, labeling a plurality of connected regions of the cell unit texture information in each HOG image, and arranging the plurality of connected regions in each HOG image in descending order of label;
s14, scanning a plurality of connected regions in each HOG image column by column to determine the position of the left and right tire boundaries;
and S15, clipping other texture information of each HOG image to obtain a tire local image.
As a preferred technical solution of the present invention, the step of finding a slope line, after fitting the slope line, dividing the slope line into a plurality of feature groups according to a specific condition to obtain a feature line, and dividing the tire pattern in the tire local image into a plurality of feature blocks according to the feature information of the feature line specifically comprises:
s21, converting each tire local image into an edge map by using the candy edge extraction, and carrying out value taking and traversal on each point in each edge map, and simultaneously searching a slope line from each edge map;
s22, performing optimization fitting on the slope lines with the same slope in each edge image, and reserving the optimal slope line;
s23, performing optimization fitting on the optimal slope line in each edge image, and keeping the longest slope line;
s24, dividing the longest slope line in each edge graph into a plurality of feature groups according to specific conditions, and processing and fitting the longest slope line in each feature group to obtain a plurality of feature lines;
and S25, carrying out blocking processing on the tire pattern of each edge map by using the characteristic information of the characteristic lines to obtain a plurality of characteristic blocks.
As a preferred technical solution of the present invention, the specific steps of comparing each feature line based on each feature block, and determining whether two feature blocks are matched to output a result are as follows:
s31, comparing each feature block of at least two edge images, calculating the similarity between each feature block of at least two edge images, and judging whether each feature block of at least two edge images is matched according to the similarity;
and S32, outputting the matching result.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
(1) the specific condition processing module of the invention utilizes numerical image processing technology, finally finds a plurality of characteristic lines by extracting the boundary characteristics of the decorative pattern, and divides the lines into a plurality of characteristic blocks, thereby being greatly convenient for comparing two images.
(2) The similarity matching module can rapidly and efficiently measure and calculate the similarity value of the images of two coaxial tires synchronously acquired by the motor vehicle, analyzes the consistency of the tire installation specifications of the same model and the wear texture state in use, and has strong practical significance for replacing the manual subjective detection mode of the quality characteristics of the motor vehicle tires.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
FIG. 1 is a schematic structural diagram of a tire pattern uniformity testing system according to the present disclosure;
FIG. 2 is a schematic diagram of a tire raw image of a tire pattern uniformity detection system according to the present disclosure;
FIG. 3 is a schematic view of a tire detail of a tire pattern uniformity detection system according to the present disclosure;
FIG. 4 is a diagram of a tire edge of a tire pattern uniformity detection system in accordance with the present disclosure;
FIG. 5 is a diagram of a tire edge meeting a length threshold and a width threshold requirement for a tire pattern uniformity detection system in accordance with the present disclosure;
FIG. 6 is a diagram of a tire edge with a first fit of a tire pattern uniformity detection system as disclosed herein;
FIG. 7 is a diagram of a tire edge having a quadratic fit according to the disclosed tire pattern uniformity detection system;
FIG. 8 is a flow chart of a method for detecting tire pattern uniformity as disclosed herein;
FIG. 9 is a flowchart illustrating a step S1 of a method for detecting tire pattern uniformity according to the present disclosure;
FIG. 10 is a flowchart illustrating a step S2 of a method for detecting tire pattern uniformity according to the present invention
Fig. 11 is a flowchart of step S3 of the method for detecting tire pattern uniformity disclosed in the present invention.
Description of reference numerals: 100. an image acquisition module; 110. an obtaining unit; 120. a normalization processing unit; 130. a mark processing unit; 140. a scanning unit; 150. a clipping unit; 200. a specific condition processing module; 210. an edge extraction unit; 220. a primary fitting unit; 230. fitting the unit again; 240. a characteristic line processing unit; 250. a block unit; 300. a similarity matching module; 310. a judgment unit; 320. and an output unit.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
Example one
Referring to the attached figure 1, the invention provides a technical scheme: a tire pattern consistency detection system comprises an image acquisition module 100, a specific condition processing module 200 and a similarity matching module 300;
the image acquisition module 100 is configured to obtain at least two original images of tires, and perform an impurity filtering process on the original images of tires to obtain at least two local images of tires.
The image acquisition module 100 comprises an obtaining unit 110, a normalization processing unit 120, a marking processing unit 130, a scanning unit 140 and a clipping unit 150, wherein the obtaining unit 110 is used for obtaining at least two tire original images, constructing at least two HOG images based on the at least two tire original images, the normalization processing unit 120 is used for carrying out normalization processing on each HOG image, removing gradient information lower than a preset threshold value in each HOG image, counting the density degree of texture information of each cell unit in each HOG image, the marking processing unit 130 is used for marking a plurality of connected regions of the texture information of the cell unit in each HOG image, the plurality of connected regions in each HOG image are arranged in sequence from large to small according to the marks, the scanning unit 140 is configured to scan the plurality of connected regions in each HOG image column by column to determine the left and right boundary positions of the tire, and the clipping unit 150 is configured to clip other texture information of each HOG image to obtain the local image of the tire.
Referring to the attached drawings 2-3, specifically, a tire original image is obtained by taking a picture of a tire by a point cloud scanner, and the tire original images of two coaxial tires of a motor vehicle are taken as a basis during the picture taking, so that the tires of the two coaxial tires can be conveniently identified in a consistency manner; because the obtained background in the original image of the tire is too large, and a part of the vehicle mud tiles can shield the tire, the tire tread needs to be cut, and the influence of the background of the original image of the tire and the mud tiles needs to be eliminated; after the normalization processing unit 120 performs normalization processing on the HOG image, the HOG image also includes other texture information; the other texture information includes surrounding vehicles and environmental debris.
When the scanning unit 140 scans, the tire area has obvious peaks due to the influence of the pattern texture of the tire area; in addition, because texture information at the water chute is not dense, the texture information may be mistaken for the boundary of the tire, and at this time, the preset threshold value is no longer applicable, and the preset threshold value needs to be modified for the HOG image.
The specific condition processing module 200 is configured to search slope lines from at least two local images of the tire, perform fitting processing, divide the slope lines into a plurality of feature groups according to specific conditions to obtain feature lines, and divide tire patterns in each edge image into a plurality of feature blocks according to feature information of the feature lines.
The specific condition processing module 200 includes an edge extracting unit 210, a first fitting unit 220, a second fitting unit 230, a feature line processing unit 240, and a partitioning unit 250, where the edge extracting unit 210 is configured to convert each tire local image into an edge map by using candy edge extraction, take values and traverse each point in each edge map, and search for a slope line from each edge map, the first fitting unit 220 is configured to perform optimal fitting on slope lines with the same slope in each edge map, retain an optimal slope line, the second fitting unit 230 is configured to perform optimal fitting on an optimal slope line in each edge map, retain a longest slope line, the feature line processing unit 240 is configured to divide the longest slope line in each edge map into a plurality of feature groups according to specific conditions, and process and fit the longest slope line in each feature group to obtain a plurality of feature lines, the blocking unit 250 is configured to perform blocking processing on the tire pattern of each edge map by using the feature information of the feature lines to obtain a plurality of feature blocks.
Specifically, referring to fig. 4 to 5, each point of each edge graph has two values (x, y) and is traversed to find a slope line in the edge graph, and the slope line also needs to satisfy the calculation condition of the unitary function; if a in the unary function is determined, each edge point (x, y) on the edge map corresponds to different b, and for the edge points with the same b, the edge points may be connected into a straight line, so that the line is searched by traversing b. By using dislocation subtraction, the dislocation subtraction judgment condition is that the difference value of x or y of one edge point and x or y of the next edge point is more than or equal to 2, namely the front and the back are considered to be two lines with different slopes; for these slope lines, length and width conditions need to be satisfied, and then the conditions that the length and the width are satisfied are that the length needs to be greater than a length threshold value, and the width needs to be greater than a width threshold value.
Referring to fig. 6, for the first fitting, if the difference between b and the slope line of the same slope is not more than 15, the two slope lines are compared, and the most effective slope line, i.e. the optimal slope line, is left.
Referring to fig. 7, for the refit, the optimal slope lines with different slopes are determined whether the lines overlap or not, and the condition, i.e., whether x or y overlaps or not, is determined, and the line with the best effect, i.e., the longest slope line, is selected from the overlapped lines.
The specific conditions are in particular the longest slope line of the position proximity, slope proximity and length proximity.
The feature information of the feature line is specifically a stored feature angle, an x coordinate of the start point, an x coordinate of the end point, a length, a minimum start point, a maximum end point, the number of the longest slope lines, and an average y of the start points.
The similarity matching module 300 is configured to receive each feature block of at least two edge maps, compare the feature blocks, determine whether each feature block of the at least two edge maps is matched, and output a result.
The similarity matching module 300 includes a judging unit 310 and an output unit 320, where the judging unit 310 is configured to compare each feature block of at least two edge maps, calculate a similarity between each feature block of the at least two edge maps, and judge whether each feature block of the at least two edge maps matches according to the similarity, and the output unit 320 is configured to output a matching result.
Specifically, when each feature block of the two edge maps is compared, it is essential that each feature block of the edge map a is compared with each feature block of the edge map B, and it is further extended that the feature lines included in each feature block of the edge map a are compared with the feature lines included in each feature block of the edge map B, and it can be determined whether the two edge maps are similar, and finally, it can be determined whether the two tire images are similar.
Example two
The embodiment of the invention also discloses a method for detecting the consistency of the tire patterns, which is shown by referring to the attached drawings 8-11 and comprises the following steps:
and S1, obtaining at least two tire original images, and carrying out impurity filtering treatment on the tire original images to obtain at least two tire local images.
In a preferred embodiment of the present invention, the obtaining of the original tire image and the obtaining of the local tire image by performing the impurity filtering process on the original tire image specifically include:
s11, obtaining at least two tire original images, and constructing at least two HOG images based on the at least two tire original images;
s12, performing normalization processing on each HOG image, removing gradient information lower than a preset threshold value in each HOG image, and counting the density of texture information of each cell unit in each HOG image;
s13, labeling a plurality of connected regions of the cell unit texture information in each HOG image, and arranging the plurality of connected regions in each HOG image in descending order of label;
s14, scanning a plurality of connected regions in each HOG image column by column to determine the position of the left and right tire boundaries;
and S15, clipping other texture information of each HOG image to obtain a tire local image.
S2, slope lines are searched from at least two tire local images and are subjected to fitting processing, the images are divided into a plurality of feature groups according to specific conditions to obtain feature lines, and tire patterns in each edge image are divided into a plurality of feature blocks according to feature information of the feature lines.
In a preferred embodiment of the present invention, the step of finding a slope line, fitting the slope line, dividing the slope line into a plurality of feature groups according to a specific condition to obtain a feature line, and dividing the tire pattern in the tire local image into a plurality of feature blocks according to the feature information of the feature line specifically comprises:
s21, converting each tire local image into an edge map by using the candy edge extraction, and carrying out value taking and traversal on each point in each edge map, and simultaneously searching a slope line from each edge map;
s22, performing optimization fitting on the slope lines with the same slope in each edge image, and reserving the optimal slope line;
s23, performing optimization fitting on the optimal slope line in each edge image, and keeping the longest slope line;
s24, dividing the longest slope line in each edge graph into a plurality of feature groups according to specific conditions, and processing and fitting the longest slope line in each feature group to obtain a plurality of feature lines;
and S25, carrying out blocking processing on the tire pattern of each edge map by using the characteristic information of the characteristic lines to obtain a plurality of characteristic blocks.
S3, receiving and comparing each feature block of at least two edge maps, judging whether each feature block of at least two edge maps is matched, and outputting a result.
In a preferred embodiment of the present invention, the specific steps of comparing each feature line based on each feature block, and determining whether two feature blocks are matched to output a result are as follows:
s31, comparing each feature block of at least two edge images, calculating the similarity between each feature block of at least two edge images, and judging whether each feature block of at least two edge images is matched according to the similarity;
and S32, outputting the matching result.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Of course, the processor and the storage medium may reside as discrete components in a user terminal.
For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in memory units and executed by processors. The memory unit may be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean "non-exclusive or".
Claims (10)
1. A tire pattern uniformity detection system, comprising:
the image acquisition module is used for synchronously acquiring at least two original images of the tire, and performing impurity filtering treatment on the original images of the tire to obtain at least two local images of the tire;
the specific condition processing module is used for searching slope lines from at least two local images of the tire, performing fitting processing, dividing the slope lines into a plurality of feature groups according to specific conditions to obtain feature lines, and dividing tire patterns in each edge image into a plurality of feature blocks according to feature information of the feature lines;
and the similarity matching module is used for receiving each feature block of at least two edge images for comparison, judging whether each feature block of the at least two edge images is matched or not and outputting a result.
2. The tire pattern uniformity detection system of claim 1, wherein said image acquisition module comprises:
an obtaining unit for obtaining at least two tire original images, and constructing at least two HOG images based on the at least two tire original images;
the normalization processing unit is used for performing normalization processing on each HOG image, removing gradient information lower than a preset threshold value in each HOG image, and counting the density of texture information of each cell unit in each HOG image;
a labeling processing unit, configured to label a plurality of connected regions of the cell unit texture information in each HOG image, and sequentially arrange the plurality of connected regions in each HOG image from large to small according to a label;
a scanning unit for scanning the plurality of connected regions in each HOG image column by column to determine tire left and right boundary positions;
and the clipping unit is used for clipping other texture information of each HOG image to obtain a tire local image.
3. The tire pattern uniformity detection system according to claim 2, wherein the specific condition processing module comprises:
the edge extraction unit is used for converting each tire local image into an edge map by using the candy edge extraction, taking values of each point in each edge map and traversing, and simultaneously searching a slope line from each edge map;
the initial fitting unit is used for carrying out optimal fitting on the slope lines with the same slope in each edge image and reserving the optimal slope line;
the refitting unit is used for performing optimal fitting on the optimal slope line in each edge image and keeping the longest slope line;
the characteristic line processing unit is used for dividing the longest slope line in each edge graph into a plurality of characteristic groups according to specific conditions, and processing and fitting the longest slope line in each characteristic group to obtain a plurality of characteristic lines;
and the blocking unit is used for carrying out blocking processing on the tire patterns of each edge image by utilizing the characteristic information of the characteristic lines to obtain a plurality of characteristic blocks.
4. A tire pattern uniformity detection system according to claim 3, wherein said specific condition is embodied by said longest slope line being located close, slope close and length close.
5. The tire pattern uniformity detection system according to claim 3, wherein the characteristic information of the characteristic line is specifically a stored characteristic angle, an x-coordinate of a start point, an x-coordinate of an end point, a length, a minimum start point, a maximum end point, a number of longest slope lines, and an average y of the start points.
6. The tire pattern uniformity detection system of claim 2, wherein the similarity matching module comprises:
the judging unit is used for comparing each feature block of at least two edge images, calculating the similarity between each feature block of at least two edge images, and judging whether each feature block of at least two edge images is matched according to the similarity;
and the output unit is used for outputting the matching result.
7. A tire pattern consistency detection method applied to the tire pattern consistency detection system of any one of claims 1 to 6, characterized by comprising the following steps:
s1, obtaining at least two tire original images, and carrying out impurity filtering processing on the tire original images to obtain at least two tire local images;
s2, slope lines are searched from at least two tire local images and are subjected to fitting processing, the images are divided into a plurality of feature groups according to specific conditions to obtain feature lines, and tire patterns in each edge image are divided into a plurality of feature blocks according to feature information of the feature lines;
s3, receiving and comparing each feature block of at least two edge maps, judging whether each feature block of at least two edge maps is matched, and outputting a result.
8. The method for detecting the consistency of the tire patterns according to claim 7, wherein the step of obtaining the original image of the tire and the step of performing the impurity filtering process on the original image of the tire to obtain the local image of the tire comprises the following specific steps:
s11, obtaining at least two tire original images, and constructing at least two HOG images based on the at least two tire original images;
s12, performing normalization processing on each HOG image, removing gradient information lower than a preset threshold value in each HOG image, and counting the density of texture information of each cell unit in each HOG image;
s13, labeling a plurality of connected regions of the cell unit texture information in each HOG image, and arranging the plurality of connected regions in each HOG image in descending order of label;
s14, scanning a plurality of connected regions in each HOG image column by column to determine the position of the left and right tire boundaries;
and S15, clipping other texture information of each HOG image to obtain a tire local image.
9. The detecting method of the tire pattern consistency detecting system according to claim 7, wherein the specific steps of finding the slope line, fitting the slope line, dividing the slope line into a plurality of feature groups according to specific conditions to obtain feature lines, and dividing the tire patterns in the tire local image into a plurality of feature blocks according to the feature information of the feature lines are as follows:
s21, converting each tire local image into an edge map by using the candy edge extraction, and carrying out value taking and traversal on each point in each edge map, and simultaneously searching a slope line from each edge map;
s22, performing optimization fitting on the slope lines with the same slope in each edge image, and reserving the optimal slope line;
s23, performing optimization fitting on the optimal slope line in each edge image, and keeping the longest slope line;
s24, dividing the longest slope line in each edge graph into a plurality of feature groups according to specific conditions, and processing and fitting the longest slope line in each feature group to obtain a plurality of feature lines;
and S25, carrying out blocking processing on the tire pattern of each edge map by using the characteristic information of the characteristic lines to obtain a plurality of characteristic blocks.
10. The method for detecting the consistency of the tire patterns according to claim 7, wherein the specific steps of comparing each feature line based on each feature block, judging whether two feature blocks are matched and outputting the result are as follows:
s31, comparing each feature block of at least two edge images, calculating the similarity between each feature block of at least two edge images, and judging whether each feature block of at least two edge images is matched according to the similarity;
and S32, outputting the matching result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111029178.5A CN113674270B (en) | 2021-09-06 | 2021-09-06 | Tire pattern consistency detection system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111029178.5A CN113674270B (en) | 2021-09-06 | 2021-09-06 | Tire pattern consistency detection system and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113674270A true CN113674270A (en) | 2021-11-19 |
| CN113674270B CN113674270B (en) | 2023-11-14 |
Family
ID=78548140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111029178.5A Active CN113674270B (en) | 2021-09-06 | 2021-09-06 | Tire pattern consistency detection system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674270B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101140624A (en) * | 2007-10-18 | 2008-03-12 | 清华大学 | Image matching method |
| CN102426649A (en) * | 2011-10-13 | 2012-04-25 | 石家庄开发区冀科双实科技有限公司 | Simple steel seal digital automatic identification method with high accuracy rate |
| WO2015141302A1 (en) * | 2014-03-17 | 2015-09-24 | オリンパス株式会社 | Image processing device, image processing method, and image processing program |
| CN106919910A (en) * | 2016-05-12 | 2017-07-04 | 江苏科技大学 | A kind of traffic sign recognition method based on HOG CTH assemblage characteristics |
| CN107239780A (en) * | 2017-04-29 | 2017-10-10 | 安徽慧视金瞳科技有限公司 | A kind of image matching method of multiple features fusion |
| EP3327470A1 (en) * | 2016-11-25 | 2018-05-30 | Nuctech Company Limited | Method of assisting analysis of radiation image and system using the same |
| US20180204111A1 (en) * | 2013-02-28 | 2018-07-19 | Z Advanced Computing, Inc. | System and Method for Extremely Efficient Image and Pattern Recognition and Artificial Intelligence Platform |
| EP3438934A1 (en) * | 2016-03-30 | 2019-02-06 | Equos Research Co., Ltd. | Image recognition device, mobile device and image recognition program |
| CN109685142A (en) * | 2018-12-25 | 2019-04-26 | 国信优易数据有限公司 | A kind of image matching method and device |
| CN109993134A (en) * | 2019-04-04 | 2019-07-09 | 中山大学 | A kind of intersection vehicle checking method based on HOG and SVM classifier |
| CN110660071A (en) * | 2019-08-23 | 2020-01-07 | 中山市奥珀金属制品有限公司 | Automatic edge detection double-threshold setting method and system |
| CN110956200A (en) * | 2019-11-05 | 2020-04-03 | 哈尔滨工程大学 | Tire pattern similarity detection method |
| JP2020190913A (en) * | 2019-05-22 | 2020-11-26 | キヤノンメディカルシステムズ株式会社 | Image-reading supporting device and method for supporting image-reading |
-
2021
- 2021-09-06 CN CN202111029178.5A patent/CN113674270B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101140624A (en) * | 2007-10-18 | 2008-03-12 | 清华大学 | Image matching method |
| CN102426649A (en) * | 2011-10-13 | 2012-04-25 | 石家庄开发区冀科双实科技有限公司 | Simple steel seal digital automatic identification method with high accuracy rate |
| US20180204111A1 (en) * | 2013-02-28 | 2018-07-19 | Z Advanced Computing, Inc. | System and Method for Extremely Efficient Image and Pattern Recognition and Artificial Intelligence Platform |
| WO2015141302A1 (en) * | 2014-03-17 | 2015-09-24 | オリンパス株式会社 | Image processing device, image processing method, and image processing program |
| EP3438934A1 (en) * | 2016-03-30 | 2019-02-06 | Equos Research Co., Ltd. | Image recognition device, mobile device and image recognition program |
| CN106919910A (en) * | 2016-05-12 | 2017-07-04 | 江苏科技大学 | A kind of traffic sign recognition method based on HOG CTH assemblage characteristics |
| EP3327470A1 (en) * | 2016-11-25 | 2018-05-30 | Nuctech Company Limited | Method of assisting analysis of radiation image and system using the same |
| CN107239780A (en) * | 2017-04-29 | 2017-10-10 | 安徽慧视金瞳科技有限公司 | A kind of image matching method of multiple features fusion |
| CN109685142A (en) * | 2018-12-25 | 2019-04-26 | 国信优易数据有限公司 | A kind of image matching method and device |
| CN109993134A (en) * | 2019-04-04 | 2019-07-09 | 中山大学 | A kind of intersection vehicle checking method based on HOG and SVM classifier |
| JP2020190913A (en) * | 2019-05-22 | 2020-11-26 | キヤノンメディカルシステムズ株式会社 | Image-reading supporting device and method for supporting image-reading |
| CN110660071A (en) * | 2019-08-23 | 2020-01-07 | 中山市奥珀金属制品有限公司 | Automatic edge detection double-threshold setting method and system |
| CN110956200A (en) * | 2019-11-05 | 2020-04-03 | 哈尔滨工程大学 | Tire pattern similarity detection method |
Non-Patent Citations (4)
| Title |
|---|
| "Optimizing automatic morphological classification of galaxies with machine learning and deep learning using Dark Energy Survey imaging", MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, vol. 493, no. 3 * |
| GAO, HUIJUN;SONG, CHUNWEI;ZHANG, HONGZHI;ZUO, WANGMENG;DENG, HONG: "Bayesian non-parametric gradient histogram estimation for texture-enhanced image deblurring", NEUROCOMPUTING, no. 12 * |
| 刘超;周激流;何坤;: "基于Canny算法的自适应边缘检测方法", 计算机工程与设计, no. 18 * |
| 陈跃;张晓光;阮殿旭;: "基于模糊梯度法的焊接图像缺陷边缘检测方法", 煤矿机械, no. 01 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113674270B (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Akagic et al. | Pavement crack detection using Otsu thresholding for image segmentation | |
| CN111145161B (en) | Pavement crack digital image processing and identifying method | |
| CN107729818B (en) | Multi-feature fusion vehicle re-identification method based on deep learning | |
| Ouma et al. | Pothole detection on asphalt pavements from 2D-colour pothole images using fuzzy c-means clustering and morphological reconstruction | |
| CN108088799B (en) | Method and system for measuring Motor vehicle exhaust Rigemann blackness | |
| CN109685760B (en) | MATLAB-based SLM powder bed powder laying image convex hull depression defect detection method | |
| CN108921813B (en) | Unmanned aerial vehicle detection bridge structure crack identification method based on machine vision | |
| CN108052904B (en) | Method and device for acquiring lane line | |
| TWI504858B (en) | A vehicle specification measuring and processing device, a vehicle specification measuring method, and a recording medium | |
| CN109858438B (en) | Lane line detection method based on model fitting | |
| CN110428425B (en) | Sea-land separation method of SAR image based on coastline vector data | |
| CN107563301A (en) | Red signal detection method based on image processing techniques | |
| CN109815961B (en) | Pavement repairing type disease detection method based on local texture binary pattern | |
| CN109614868B (en) | Automobile tire pattern image straight line recognition system | |
| CN111027544A (en) | MSER license plate positioning method and system based on visual saliency detection | |
| CN114926410A (en) | Method for detecting appearance defects of brake disc | |
| CN111932494B (en) | Tire wear degree evaluation method and device | |
| CN1290049C (en) | Method for automatically extracting image feature points of workpiece with rough grain under the strong reflection background | |
| CN108268866B (en) | Vehicle detection method and system | |
| CN103544495A (en) | Method and system for recognizing of image categories | |
| CN112950594A (en) | Method and device for detecting surface defects of product and storage medium | |
| CN113674270A (en) | Tire pattern consistency detection system and method | |
| Buck et al. | Enhanced ship detection from overhead imagery | |
| CN112069924A (en) | Lane line detection method, lane line detection device and computer-readable storage medium | |
| CN116681912A (en) | Rail gauge detection method and device for railway turnout |
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 | ||
| CB02 | Change of applicant information |
Address after: 266000 building 7, Qingdao Tiangu Industrial Park, Chengyang District, Qingdao City, Shandong Province Applicant after: Shenbang Intelligent Technology Group (Qingdao) Co.,Ltd. Address before: 266000 building 7, Qingdao Tiangu Industrial Park, Chengyang District, Qingdao City, Shandong Province Applicant before: SHENBANG INTELLIGENT TECHNOLOGY (QINGDAO) CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A tire pattern consistency detection system and its method Granted publication date: 20231114 Pledgee: Weihai commercial bank Limited by Share Ltd. Qingdao branch Pledgor: Shenbang Intelligent Technology Group (Qingdao) Co.,Ltd. Registration number: Y2024980011683 |