CN113379688A - Stabilizer bar hole deviation detection method and system based on image recognition - Google Patents
Stabilizer bar hole deviation detection method and system based on image recognition Download PDFInfo
- Publication number
- CN113379688A CN113379688A CN202110596698.8A CN202110596698A CN113379688A CN 113379688 A CN113379688 A CN 113379688A CN 202110596698 A CN202110596698 A CN 202110596698A CN 113379688 A CN113379688 A CN 113379688A
- Authority
- CN
- China
- Prior art keywords
- information
- virtual
- circle center
- hole
- positioning hole
- 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
- 239000003381 stabilizer Substances 0.000 title claims abstract description 66
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 27
- 238000012958 reprocessing Methods 0.000 claims description 19
- 238000005070 sampling Methods 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000001939 inductive effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 238000003754 machining Methods 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 238000005282 brightening Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000005096 rolling process 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
- G06T7/0004—Industrial image inspection
-
- 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
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the field of workpiece detection, and provides a method and a system for detecting the deviation of a stabilizer bar hole based on image recognition, aiming at the problem that the judgment is difficult when the deviation of a positioning hole is recognized by naked eyes; the method comprises the following steps: acquiring basic image information of positioning holes at two ends of the fixed stabilizer bar; preprocessing basic image information to obtain intermediate-level image information, wherein the preprocessing comprises noise reduction and burr removal; obtaining virtual circle center position information and virtual radius information of the positioning hole according to the intermediate-level image information; and judging whether the positioning hole deviates according to the virtual circle center position information and preset standard circle center position information to obtain positioning hole judgment information, wherein the positioning hole judgment information is that the positioning hole deviates or the positioning hole does not deviate.
Description
Technical Field
The invention belongs to the field of workpiece detection, and particularly relates to a stabilizer bar hole deviation detection method and system based on image recognition.
Background
The stabilizer bar device is arranged between an automobile auxiliary frame and a suspension frame and used for balancing an automobile body and preventing the automobile body from generating overlarge transverse rolling when turning. The common automobile stabilizer bar device adopts a stabilizer bar connecting rod to connect a stabilizer bar body with a strut assembly, the stabilizer bar connecting rod adopts a ball head and is connected with the stabilizer bar body through a nut, and the stabilizer bar body is installed on an auxiliary frame through a stabilizer bar bushing and a stabilizer bar bracket.
The existing stabilizer bar is U-shaped, two ends of the stabilizer bar are symmetrically bent, positioning holes are formed in the end heads of the stabilizer bar, one section in the middle of the stabilizer bar is a middle straight rod part of the stabilizer bar, the middle straight rod part of the stabilizer bar is inserted into a stabilizer bar bushing, and the suspension stabilizer bar is fixedly arranged on a vehicle body or a vehicle frame; the positioning holes are used for limiting bevel gear members sleeved at two ends of the stabilizer bar. Whether the positioning hole is deviated or not affects the connection of the entire stabilizer bar to the entire vehicle and the stability of the entire vehicle body when the vehicle is running. For this reason, how to judge whether the positioning hole of the stabilizer bar deviates from a preset position at the time of manufacturing and whether the circumference of the positioning hole is smooth is an important part in quality evaluation of the stabilizer bar.
Disclosure of Invention
The invention provides a stabilizer bar hole deviation detection method and system based on image recognition, and solves the problems that in the prior art, judgment is difficult and inaccurate when a positioning hole is recognized by naked eyes.
The basic scheme provided by the invention is as follows: a stabilizer bar hole deviation detection method based on image recognition comprises the following steps:
acquiring basic image information of positioning holes at two ends of the fixed stabilizer bar;
preprocessing basic image information to obtain intermediate-level image information, wherein the preprocessing comprises noise reduction and burr removal;
obtaining virtual circle center position information and virtual radius information of the positioning hole according to the intermediate-level image information;
judging whether the positioning hole deviates according to the virtual circle center position information and preset standard circle center position information to obtain positioning hole judgment information, wherein the positioning hole judgment information is that the positioning hole deviates or the positioning hole does not deviate;
obtaining virtual hole periphery information according to the virtual circle center position information and the virtual radius information;
calculating the pixel ratio of the superposition of the basic image information and the virtual hole periphery information according to the virtual hole periphery information and the basic image information;
and judging whether the positioning hole is poor or not according to the pixel ratio to obtain hole periphery judging information, wherein the hole periphery judging information is the positioning hole poor or the positioning hole good.
Has the advantages that: in the scheme, the noise and burr of the basic image information are reduced through preprocessing, so that the subsequent determination of the virtual circle center position is facilitated, and the accuracy of the determination of the virtual circle center position is improved. Then, the virtual circle center is formulated and referred to information points of most edges in the intermediate-level image information, the virtual circle center is very close to the real circle center, the deviation degree (such as the distance between the virtual circle center and the standard circle center) between the virtual circle center and the standard circle center is known through position comparison between the virtual circle center and the standard circle center, and whether the deviation condition of the whole positioning hole occurs or not is judged according to the deviation degree. The automatic detection and judgment of whether the whole positioning hole deviates from the standard circle center is fully realized, and the fault which can occur during the observation of the naked eyes is avoided.
The virtual hole circumference information is a set of all pixel points on a virtual circle drawn by taking the position of the virtual circle center as the circle center and the virtual radius information as the radius; calculating the proportion of the number of overlapped pixel points in the two pixel point sets of the virtual hole periphery information and the basic hole periphery information to the number of all the pixel points, and taking the proportion as the pixel ratio of the basic image information to the virtual hole periphery information; the higher the pixel ratio is, the higher the coincidence degree between the basic image information and the virtual hole circumference information is proved to be, that is, the more the edge of the positioning hole corresponding to the basic image information approaches to a perfect circle, the better the positioning hole circumference judgment information is set as the positioning hole is; correspondingly, the lower the pixel ratio, the lower the coincidence degree between the basic image information and the virtual hole periphery information is, the hole periphery of the positioning hole corresponding to the basic image information does not tend to be a perfect circle, and the hole periphery judgment information is set as a positioning hole failure. This scheme has been realized, whether there is bad automatic judgement to the edge of locating hole, and the burr and the breach of judgement locating hole that can be clear are compared artifical naked eye discernment and are regarded as the precision higher.
Further, the stable dry hole deviation detection method further comprises:
calculating the pixel deviation degree between the basic image information and the virtual hole periphery information according to the virtual hole periphery information and the basic image information;
and obtaining workpiece reprocessing feasibility information according to the pixel deviation degree, wherein the workpiece reprocessing feasibility information is that the workpiece can be machined or cannot be reprocessed.
Has the advantages that: according to the scheme, on the basis of the above, the pixel deviation degree between the basic image information and the virtual hole periphery information is calculated; pixels in the basic image information correspond to pixels in the virtual hole periphery information one by one, the pixels in the basic image information correspond to pixels in the unique virtual hole periphery information, and the pixels in the virtual hole periphery information also correspond to pixels in the unique basic image information (the pixels in the virtual hole periphery information do not correspond to the pixels in the basic image information, and the pixels in the basic image information do not correspond to the pixels in the virtual hole periphery information), so that the sum of distances between the pixels in all the mutually corresponding basic image information and the pixels in the virtual hole periphery information is ensured to be minimum.
When the pixel in the corresponding basic image information is positioned between the pixel in the virtual hole periphery information and the pixel between the virtual circle centers, setting the distance between the pixel in the basic image information and the pixel in the virtual hole periphery information as a positive number; otherwise it is negative. The foregoing distance is set as the pixel deviation degree. And then, obtaining workpiece reprocessing feasibility information according to the pixel deviation degree, wherein the workpiece reprocessing feasibility information is that the workpiece can be processed or the workpiece cannot be reprocessed.
For example: when all the pixel deviation degrees are greater than or equal to 0, the workpiece is judged to be machinable, namely, the workpiece reprocessing feasibility information is that the workpiece can be processed; otherwise, the information of the machining feasibility of the workpiece is set as that the workpiece can not be machined.
Further, the stable dry hole deviation detection method further comprises:
when the hole periphery judgment information indicates that the positioning hole is bad,
and executing the step of calculating the pixel deviation degree between the basic image information and the virtual hole periphery information according to the virtual hole periphery information and the basic image information.
Has the advantages that: according to the scheme, the subsequent processing feasibility judgment of the workpiece is carried out only when the hole periphery judgment information is that the positioning hole is poor, compared with the simultaneous judgment, the overall workload is reduced, and the execution speed of the whole stabilizer bar hole deviation detection method is improved.
Further, the obtaining of the virtual circle center position information and the virtual radius information of the positioning hole according to the intermediate-level image information specifically includes:
detecting an image edge from the intermediate-level image information, and capturing a sampling point;
calculating the current circle center virtual position of each group by taking the three sampling points as a group;
according to all the current virtual positions of the circle center, summarizing virtual circle center position information;
and calculating the average value of the distances from the virtual circle center position information to each sampling point, and calculating virtual radius information.
Further, the inducing virtual circle center position information according to all the current circle center virtual positions includes:
and screening out the current circle center virtual position with the shortest distance to other current circle center virtual positions from all the current circle center virtual positions as virtual circle center position information.
Further, the inducing virtual circle center position information according to all the current circle center virtual positions includes:
and setting virtual circle center position information to ensure that the distance between the virtual circle center position information and all current circle center virtual positions is shortest.
Further, the inducing virtual circle center position information according to all the current circle center virtual positions includes:
and setting virtual circle center position information to ensure that the sum of the square differences between every two virtual circle center positions and the distances between the virtual circle center position information and all current circle center virtual positions is minimum.
The invention also provides a stabilizer bar hole deviation detection system based on image recognition, which comprises:
the limiting module is used for limiting the spatial position of the stabilizer bar;
the image acquisition module is used for acquiring basic image information of positioning holes at two ends of the stabilizer bar after the limiting module is fixed;
the image processing module is used for executing any one of the stabilizer bar hole deviation detection methods based on image recognition and outputting hole deviation detection result information; the hole deviation detection result information comprises at least one of positioning hole judgment information, hole periphery judgment information and workpiece reprocessing feasibility information.
Further, the image processing module includes:
the first image processing unit is used for preprocessing the basic image information to obtain intermediate-level image information;
the second image processing unit is used for obtaining the virtual circle center position information and the virtual radius information of the positioning hole according to the intermediate image information; and obtaining positioning hole judgment information according to the virtual circle center position information and preset standard circle center position information, wherein the positioning hole judgment information is that the positioning hole deviates or the positioning hole does not deviate.
Further, the second image processing unit is further configured to obtain hole periphery judgment information according to the virtual circle center position information and preset standard circle center position information, where the hole periphery judgment information is that a positioning hole is bad or a positioning hole is good.
Further, the second image processing unit is further configured to calculate a pixel deviation degree between the basic image information and the virtual hole periphery information according to the virtual hole periphery information and the basic image information; and obtaining workpiece reprocessing feasibility information according to the pixel deviation degree, wherein the workpiece reprocessing feasibility information is that the workpiece can be machined or cannot be reprocessed.
Drawings
Fig. 1 is a schematic flow chart of a stabilizer bar hole deviation detection method based on image recognition according to a first embodiment of the present invention;
fig. 2 is a schematic block diagram of a stabilizer bar hole deviation detecting system based on image recognition according to a second embodiment of the present invention;
FIG. 3 is a schematic structural diagram of the position limiting module in FIG. 2;
fig. 4 is a schematic diagram of data processing of the second image processing unit in fig. 2.
Detailed Description
The following is further detailed by the specific embodiments:
in order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
The first embodiment:
the first embodiment of the invention provides a stabilizer bar hole deviation detection method based on image recognition, which comprises the following steps: acquiring basic image information of positioning holes at two ends of the fixed stabilizer bar; preprocessing basic image information to obtain intermediate-level image information, wherein the preprocessing comprises noise reduction and burr removal; obtaining virtual circle center position information and virtual radius information of the positioning hole according to the intermediate-level image information; and judging whether the positioning hole deviates according to the virtual circle center position information and preset standard circle center position information to obtain positioning hole judgment information, wherein the positioning hole judgment information is that the positioning hole deviates or the positioning hole does not deviate.
The basic image information is subjected to noise reduction and burr removal through preprocessing, so that the subsequent determination of the virtual circle center position is facilitated, and the accuracy of the determination of the virtual circle center position is improved. Then, the virtual circle center is formulated and referred to information points of most edges in the intermediate-level image information, the virtual circle center is very close to the real circle center, the deviation degree (such as the distance between the virtual circle center and the standard circle center) between the virtual circle center and the standard circle center is known through position comparison between the virtual circle center and the standard circle center, and whether the deviation condition of the whole positioning hole occurs or not is judged according to the deviation degree. The automatic detection and judgment of whether the whole positioning hole deviates from the standard circle center is fully realized, and the fault which can occur during the observation of the naked eyes is avoided.
The following describes implementation details of the stabilizer bar hole deviation detection method based on image recognition, and the following only provides implementation details for easy understanding, but is not essential to implementing the present embodiment, and a specific flow of the present embodiment is shown in fig. 1, and the present embodiment is applied to a stabilizer bar hole deviation detection system based on image recognition.
And S1, acquiring basic image information of the positioning holes at the two ends of the fixed stabilizer bar.
Specifically, the stabilizer bar is fixed by a limiting module in a stabilizer bar hole deviation detection system based on image recognition (the shape and structure of the limiting module are shown in fig. 3), the position of the stabilizer bar is fixed, and the fixed stabilizer bar is limited in space and cannot easily move. The implementation of step S1 is: and image acquisition modules are arranged near the positioning holes at the two ends of the stabilizer bar and used for acquiring images of areas where the positioning holes corresponding to the image acquisition modules are located and setting the images as basic image information. Therefore, in the two positioning holes of the fixing rod, each positioning hole corresponds to unique basic image information.
And S2, preprocessing the basic image information to obtain intermediate-level image information, wherein the preprocessing comprises noise reduction and burr removal.
Specifically, the basic image information is preprocessed, so that subsequent image recognition is facilitated, and images around the positioning holes in the basic image information are clear. The pre-treatment process includes noise reduction, deburring or brightening.
Wherein the basic image information is enhancedThe brightness process comprises the steps of obtaining gray data of each pixel in basic image information; calculating the average gray value of a plurality of pixel points at the central position in the basic image information; calculating a parameter value of a predetermined parameter according to a first formula, where γ ═ log (Ga) -1, Ga is the average gray-scale value, and γ is the predetermined parameter; adjusting the brightness value of each color channel of each pixel point in the basic image information by using a second formula, wherein the second formula is as follows:
wherein A is the brightness value of any color channel of any pixel point in the basic image information, and A is the brightness value of any color channel of any pixel point in the basic image informationGammaThe adjusted brightness value of any color channel of any pixel point is obtained. However, the processes of noise reduction and burr removal for the basic image information are already widely used by image editing software, such as american show, and the like, and the applicant does not make much expression on the method of noise reduction and burr removal according to the present scheme without modification. Therefore, the method for reducing noise and removing burrs in the step can be realized by adopting a microprocessor, and the microprocessor is loaded with image editing software for reducing noise and removing burrs.
And S3, obtaining the virtual circle center position information and the virtual radius information of the positioning hole according to the intermediate-level image information.
Specifically, detecting an image edge from the intermediate image information, and capturing a sampling point; calculating the current circle center virtual position of each group by taking the three sampling points as a group; according to all the current virtual positions of the circle center, summarizing virtual circle center position information; and calculating the average value of the distances from the virtual circle center position information to each sampling point, and calculating virtual radius information.
The method comprises the following steps of summarizing virtual circle center position information according to all current circle center virtual positions, and comprises the following specific steps:
firstly, screening out the current circle center virtual position with the shortest distance to other current circle center virtual positions from all the current circle center virtual positions as virtual circle center position information. The method is characterized in that a current circle center virtual position meeting the requirement is screened out from all current circle center virtual positions, and the screening condition is that the sum of the distances from the current circle center virtual position to other current circle center virtual positions is shortest.
And secondly, setting virtual circle center position information to ensure that the distance between the virtual circle center position information and all current circle center virtual positions is shortest. The method is characterized in that a virtual circle center position is reset on the basis of all current circle center virtual positions, the setting requirement of the virtual circle center position is that the distance between the virtual circle center position information and all current circle center virtual positions is the shortest, and the virtual circle center position can be ensured to correspond to the center of a positioning hole as far as possible.
And thirdly, setting virtual circle center position information to ensure that the sum of squared differences between every two virtual circle center positions and the distances between the virtual circle center position information and all current circle center virtual positions is minimum.
And S4, judging whether the positioning hole deviates or not according to the virtual circle center position information and the preset standard circle center position information to obtain positioning hole judgment information, wherein the positioning hole judgment information is that the positioning hole deviates or does not deviate.
Specifically, the information of the virtual circle center position refers to information points of most edges in the intermediate-level image information, the virtual circle center position information is very close to the real circle center, the deviation degree (such as the distance from the virtual circle center to the standard circle center) between the virtual circle center position information and the standard circle center position information is known through position comparison between the virtual circle center position information and the standard circle center position information, and whether the whole positioning hole deviates or not is judged according to the deviation degree. The standard circle center position information is preset by a worker, is usually an input value or a built-in value, and cannot be changed during operation.
In the implementation stage, a standard deviation distance k is usually set, the actual distance between the virtual circle center position information and the standard circle center position information is calculated as a current deviation distance d, the magnitude of the current deviation distance d represents the deviation degree, and the larger the value of d is, the larger the deviation becomes; and when d is larger than or equal to k, judging that the current deviation distance d exceeds the preset standard deviation distance k, namely, the deviation degree exceeds the allowable error range, and setting the positioning hole judgment information as the positioning hole deviation. Otherwise, the positioning hole judgment information is set to be that the positioning hole does not deviate.
And S5, obtaining the virtual hole circumference information according to the virtual circle center position information and the virtual radius information after the step S3 is completed.
Specifically, a virtual circle is drawn with the virtual center position calculated in S3 as the center and the virtual radius information as the radius, and the set of all the pixels on the virtual circle is used as the virtual hole circumference information.
S6, based on the virtual hole periphery information and the basic image information, calculates a pixel ratio at which the basic image information and the virtual hole periphery information overlap each other.
Specifically, on the basis of the completion of the step S5, the ratio of the number of the superimposable pixels in the two pixel sets of the virtual hole perimeter information and the basic hole perimeter information to the number of all the pixels is calculated, and the ratio is used as the pixel ratio of the superposition of the basic image information and the virtual hole perimeter information; the higher the pixel ratio is, the higher the coincidence degree between the basic image information and the virtual hole circumference information is proved to be, that is, the more the edge of the positioning hole corresponding to the basic image information approaches to a perfect circle, the better the positioning hole circumference judgment information is set as the positioning hole is; correspondingly, the lower the pixel ratio, the lower the coincidence degree between the basic image information and the virtual hole periphery information is, the hole periphery of the positioning hole corresponding to the basic image information does not tend to be a perfect circle, and the hole periphery judgment information is set as a positioning hole failure.
S7, calculating the pixel deviation degree between the basic image information and the virtual hole periphery information according to the virtual hole periphery information and the basic image information; and obtaining workpiece reprocessing feasibility information according to the pixel deviation degree, wherein the workpiece reprocessing feasibility information is that the workpiece can be machined or cannot be reprocessed.
Specifically, after the completion of step S5, the pixel shift m between the base image information and the virtual hole circumference information is calculated.
The process of calculating the pixel deviation m is as follows: pixels in the basic image information correspond to pixels in the virtual hole periphery information one by one, the pixels in the basic image information correspond to pixels in the unique virtual hole periphery information, and the pixels in the virtual hole periphery information also correspond to pixels in the unique basic image information (the pixels in the virtual hole periphery information do not correspond to the pixels in the basic image information, and the pixels in the basic image information do not correspond to the pixels in the virtual hole periphery information), so that the sum of distances between the pixels in all the mutually corresponding basic image information and the pixels in the virtual hole periphery information is ensured to be minimum. When the pixel in the corresponding basic image information is positioned between the pixel in the virtual hole periphery information and the pixel between the virtual circle centers, setting the distance between the pixel in the basic image information and the pixel in the virtual hole periphery information as a positive number; otherwise it is negative. The foregoing distance is set to the pixel deviation degree m.
And then, obtaining workpiece reprocessing feasibility information according to the pixel deviation degree m, wherein the workpiece reprocessing feasibility information is that the workpiece can be processed or the workpiece cannot be reprocessed. For example: when all the pixel deviation degrees m are greater than or equal to 0, the workpiece is judged to be machinable, namely, the workpiece reprocessing feasibility information is that the workpiece can be processed; otherwise, the information of the machining feasibility of the workpiece is set as that the workpiece can not be machined.
In some embodiments, after steps S5 and S6 are executed, step S7 is executed according to the content of the hole cycle judgment information in S6: and when the hole circumference judgment information indicates that the positioning hole is bad, executing the step of calculating the pixel deviation degree between the basic image information and the virtual hole circumference information according to the virtual hole circumference information and the basic image information. According to the scheme, the subsequent processing feasibility judgment of the workpiece is carried out only when the hole periphery judgment information is that the positioning hole is poor, compared with the simultaneous judgment, the whole workload is reduced, and the execution speed of the whole stabilizer bar hole deviation detection method is improved.
Second embodiment:
the second embodiment of the present invention further provides a stabilizer bar hole deviation detecting system based on image recognition, as shown in fig. 2, including:
a limiting module 21 for limiting a spatial position of the stabilizer bar;
the image acquisition module 22 is used for acquiring basic image information of positioning holes at two ends of the stabilizer bar after the limiting module 21 is fixed and sending the basic image information to the display module 25;
and the display module 25 is used for displaying the basic image information of the positioning hole sent by the image acquisition module 22.
An image processing module 23, configured to send hole deviation detection result information to an output module, for the stabilizer bar hole deviation detection method based on image recognition according to any one of the first embodiments; the hole deviation detection result information comprises at least one of positioning hole judgment information, hole periphery judgment information and workpiece reprocessing feasibility information;
and the output module 24 is configured to output the hole deviation detection result information sent by the image processing module 23.
Specifically, the image processing module 23 includes:
a first image processing unit 231, configured to pre-process the basic image information to obtain intermediate-level image information;
the second image processing unit 232 is configured to obtain virtual circle center position information and virtual radius information of the positioning hole according to the intermediate-level image information; according to the virtual circle center position information and the virtual radius information, hole deviation detection result information is obtained, and the method specifically comprises the following steps:
obtaining positioning hole judgment information according to the virtual circle center position information and preset standard circle center position information, wherein the positioning hole judgment information is that a positioning hole deviates or the positioning hole does not deviate;
and/or obtaining hole periphery judgment information according to the virtual circle center position information and preset standard circle center position information, wherein the hole periphery judgment information is that a positioning hole is poor or the positioning hole is good;
and/or calculating the pixel deviation degree between the basic image information and the virtual hole periphery information; and obtaining workpiece reprocessing feasibility information according to the pixel deviation degree, wherein the workpiece reprocessing feasibility information is that the workpiece can be machined or cannot be reprocessed.
In the implementation stage, the position limiting module 21 is implemented by using a device as shown in fig. 3, the device includes two main support members 212 and two auxiliary support members 213 mounted on the working table 211, one of the main support members 212 is provided, the auxiliary support members 213 are provided at two ends of the main support member 212, the two auxiliary support members 213 have the same shape and structure, and the two auxiliary support members 213 are oppositely disposed with the main support member 212 as the center. The main supporting member 212 includes two supporting posts 2121 and a clamping member 2122, the clamping member 2122 is located between the two supporting posts 2121, the upper end surfaces of the two ends of the clamping member 2122 are respectively provided with a first limiting groove, the upper end surfaces of the two supporting posts are also respectively provided with a second limiting groove and a third limiting groove, and the inner walls of the first limiting groove, the second limiting groove and the third limiting groove are fitted with the surface of the middle portion of the standard stabilizer bar 3. The top end of the auxiliary support 213 is provided with a seating groove, which is engaged with the surfaces of both ends of the standard stabilizer bar 3. Thus, the entire stabilizer bar can be restrained by the device described in fig. 3.
The image collecting module 22 may be implemented by collecting images of the positioning holes at the two ends of the stabilizer bar by using an infrared camera, for example, the infrared camera is installed at the top end of the auxiliary supporting member 213 in the limiting module 21 shown in fig. 3, so as to collect images of the positioning holes at the two ends of the stabilizer bar; when the positioning holes at the two ends of the stabilizer bar are shielded by the mounting groove of the auxiliary support 213 when being limited by the limiting module 21, the infrared camera can be even mounted in the groove of the inner wall of the mounting groove, thereby realizing image acquisition of the area where the positioning holes at the two ends of the stabilizer bar are located.
The display module 25 is usually implemented by using a display screen to display, and displays the basic image information sent by the image acquisition module 22 where two infrared cameras are located according to the positions of the infrared cameras during displaying. That is, the display module 25 simultaneously displays the basic image information transmitted by the two image capturing modules 22, the basic image information transmitted by the image capturing module 22 on the left side is displayed on the left portion of the screen, and the basic image information transmitted by the image capturing module 22 on the right side is displayed on the right portion of the screen.
The image processing module 23 is generally executed by a microprocessor loaded with a program for implementing all the stabilizer bar hole deviation detection methods based on image recognition according to the first embodiment, and the corresponding first image processing unit 231 and second image processing unit 232 are part of the program. In other words, the image processing module 23 usually employs a PCB board, and the PCB board is provided with two microprocessors, a first microprocessor is used for loading the function corresponding to the first image processing unit 231, and a second microprocessor is used for loading the function corresponding to the second image processing unit 232. The function of the second image processing unit 232 loaded by the second microprocessor is a process of processing the middle-level image information sent by the first microprocessor to obtain the positioning hole judgment information, as shown in fig. 4, which specifically includes the following steps: firstly, sorting all the middle-level image information according to the numbering of each middle-level image information, wherein each middle-level image information corresponds to one number; then, randomly sampling from the intermediate image information to obtain position information of a plurality of sampling points, wherein the position information of the sampling points corresponds to the coordinate points in the graph 4; then, according to the position information of the sampling points, calculating virtual circle center position information (not shown in fig. 4) and virtual radius information of a plurality of groups of positioning holes, wherein the virtual radius information corresponds to the distance from the center to the edge of the hole in fig. 4; secondly, calculating the distances among the virtual circle center position information of the multiple groups of positioning holes in a lump to obtain the integral virtual circle center position information; and finally, calculating the distance between the overall virtual circle center position information and the preset standard circle center position information (corresponding to the distance between the circle centers in the graph 4) to obtain positioning hole judgment information, wherein the positioning hole judgment information is that the positioning hole deviates or the positioning hole does not deviate.
An output module 24, which is usually a data interface with physical properties, for outputting the hole deviation detection result information; or a wireless antenna is adopted to send the hole deviation detection result information to the related management personnel through a wireless network/a wired network.
It should be understood that this embodiment is a system example corresponding to the first embodiment, and this embodiment may be implemented in cooperation with the first embodiment, and is not described herein again to reduce redundancy. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the first embodiment.
It should be noted that, in the present embodiment, each unit is a logical unit, and in practical applications, one logical unit may be one physical unit, may be a part of one physical unit, and may be implemented by a combination of a plurality of physical units. In addition, in order to highlight the innovative part of the present invention, elements that are not so closely related to solving the technical problems proposed by the present invention are not introduced in the present embodiment, but this does not indicate that other elements are not present in the present embodiment.
The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is not described herein in any greater extent than that known in the art at the filing date or prior to the priority date of the application, so that those skilled in the art can now appreciate that all of the above-described techniques in this field and have the ability to apply routine experimentation before this date can be combined with one or more of the present teachings to complete and implement the present invention, and that certain typical known structures or known methods do not pose any impediments to the implementation of the present invention by those skilled in the art. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (9)
1. A stabilizer bar hole deviation detection method based on image recognition is characterized by comprising the following steps:
acquiring basic image information of positioning holes at two ends of the fixed stabilizer bar;
preprocessing basic image information to obtain intermediate-level image information, wherein the preprocessing comprises noise reduction and burr removal;
obtaining virtual circle center position information and virtual radius information of the positioning hole according to the intermediate-level image information;
judging whether the positioning hole deviates according to the virtual circle center position information and preset standard circle center position information to obtain positioning hole judgment information, wherein the positioning hole judgment information is that the positioning hole deviates or the positioning hole does not deviate;
obtaining virtual hole periphery information according to the virtual circle center position information and the virtual radius information;
calculating the pixel ratio of the superposition of the basic image information and the virtual hole periphery information according to the virtual hole periphery information and the basic image information;
and judging whether the positioning hole is poor or not according to the pixel ratio to obtain hole periphery judging information, wherein the hole periphery judging information is the positioning hole poor or the positioning hole good.
2. The method of claim 1, wherein the method comprises: the stable dry hole deviation detection method further comprises the following steps:
calculating the pixel deviation degree between the basic image information and the virtual hole periphery information according to the virtual hole periphery information and the basic image information;
and obtaining workpiece reprocessing feasibility information according to the pixel deviation degree, wherein the workpiece reprocessing feasibility information is that the workpiece can be machined or cannot be reprocessed.
3. The method of claim 2, further comprising:
when the hole periphery judgment information indicates that the positioning hole is bad,
and executing the step of calculating the pixel deviation degree between the basic image information and the virtual hole periphery information according to the virtual hole periphery information and the basic image information.
4. The method as claimed in claim 1, wherein the obtaining of the virtual center position information and the virtual radius information of the positioning hole according to the intermediate-level image information specifically includes:
detecting an image edge from the intermediate-level image information, and capturing a sampling point;
calculating the current circle center virtual position of each group by taking the three sampling points as a group;
according to all the current virtual positions of the circle center, summarizing virtual circle center position information;
and calculating the average value of the distances from the virtual circle center position information to each sampling point, and calculating virtual radius information.
5. The method as claimed in claim 4, wherein the step of summarizing virtual circle center position information according to all current circle center virtual positions includes:
and screening out the current circle center virtual position with the shortest distance to other current circle center virtual positions from all the current circle center virtual positions as virtual circle center position information.
6. The method as claimed in claim 4, wherein the step of summarizing virtual circle center position information according to all current circle center virtual positions includes:
and setting virtual circle center position information to ensure that the distance between the virtual circle center position information and all current circle center virtual positions is shortest.
7. The method as claimed in claim 4, wherein the step of summarizing virtual circle center position information according to all current circle center virtual positions includes:
and setting virtual circle center position information to ensure that the sum of the square differences between every two virtual circle center positions and the distances between the virtual circle center position information and all current circle center virtual positions is minimum.
8. A stabilizer bar hole deviation detection system based on image recognition is characterized by comprising:
the limiting module is used for limiting the spatial position of the stabilizer bar;
the image acquisition module is used for acquiring basic image information of positioning holes at two ends of the stabilizer bar after the limiting module is fixed;
the image processing module is used for executing the stabilizer bar hole deviation detection method based on image recognition in any one of claims 1-7 and outputting hole deviation detection result information; the hole deviation detection result information comprises at least one of positioning hole judgment information, hole periphery judgment information and workpiece reprocessing feasibility information.
9. The stabilizer bar hole deviation detecting system based on image recognition of claim 8, wherein the image processing module comprises:
the first image processing unit is used for preprocessing the basic image information to obtain intermediate-level image information;
the second image processing unit is used for obtaining the virtual circle center position information and the virtual radius information of the positioning hole according to the intermediate image information; and obtaining positioning hole judgment information according to the virtual circle center position information and preset standard circle center position information, wherein the positioning hole judgment information is that the positioning hole deviates or the positioning hole does not deviate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110596698.8A CN113379688B (en) | 2021-05-28 | 2021-05-28 | Stabilizer bar hole deviation detection method and system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110596698.8A CN113379688B (en) | 2021-05-28 | 2021-05-28 | Stabilizer bar hole deviation detection method and system based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113379688A true CN113379688A (en) | 2021-09-10 |
| CN113379688B CN113379688B (en) | 2023-12-08 |
Family
ID=77574876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110596698.8A Active CN113379688B (en) | 2021-05-28 | 2021-05-28 | Stabilizer bar hole deviation detection method and system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113379688B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699217A (en) * | 2009-11-03 | 2010-04-28 | 武汉大学 | Method used for detecting concentric circle of industrial part |
| CN105488803A (en) * | 2015-12-09 | 2016-04-13 | 重庆康华瑞明科技股份有限公司 | Human eye pupil image judgment method |
| KR20160052145A (en) * | 2014-11-04 | 2016-05-12 | 경북대학교 산학협력단 | System and Method for Testing Hole Expansion for Sheet Materials Using Pattern Recognition Technique |
| WO2017088309A1 (en) * | 2015-11-27 | 2017-06-01 | 西安中兴新软件有限责任公司 | Method and apparatus for moving icon, and computer storage medium |
| CN107529278A (en) * | 2016-06-16 | 2017-12-29 | De&T株式会社 | Apparatus for correcting position of work-piece and its method |
| CN108537153A (en) * | 2018-03-27 | 2018-09-14 | 华南农业大学 | A kind of detection of log board hole defect and localization method based on ellipse fitting |
| CN109461044A (en) * | 2018-09-21 | 2019-03-12 | 南京林业大学 | Customize the mistake proofing checking method and its device of the board-like part processing hole location of household |
| CN110020396A (en) * | 2017-09-19 | 2019-07-16 | 桂林电子科技大学 | A kind of concentricity assessment method based on Tolerance Principle |
| CN110390696A (en) * | 2019-07-03 | 2019-10-29 | 浙江大学 | A kind of circular hole pose visible detection method based on image super-resolution rebuilding |
| CN111896221A (en) * | 2020-07-30 | 2020-11-06 | 四川大学 | Alignment method of rotating optical measurement system for virtual coordinate system auxiliary camera calibration |
| CN112001917A (en) * | 2020-09-04 | 2020-11-27 | 南京大学金陵学院 | Machine vision-based geometric tolerance detection method for circular perforated part |
-
2021
- 2021-05-28 CN CN202110596698.8A patent/CN113379688B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699217A (en) * | 2009-11-03 | 2010-04-28 | 武汉大学 | Method used for detecting concentric circle of industrial part |
| KR20160052145A (en) * | 2014-11-04 | 2016-05-12 | 경북대학교 산학협력단 | System and Method for Testing Hole Expansion for Sheet Materials Using Pattern Recognition Technique |
| WO2017088309A1 (en) * | 2015-11-27 | 2017-06-01 | 西安中兴新软件有限责任公司 | Method and apparatus for moving icon, and computer storage medium |
| CN105488803A (en) * | 2015-12-09 | 2016-04-13 | 重庆康华瑞明科技股份有限公司 | Human eye pupil image judgment method |
| CN107529278A (en) * | 2016-06-16 | 2017-12-29 | De&T株式会社 | Apparatus for correcting position of work-piece and its method |
| CN110020396A (en) * | 2017-09-19 | 2019-07-16 | 桂林电子科技大学 | A kind of concentricity assessment method based on Tolerance Principle |
| CN108537153A (en) * | 2018-03-27 | 2018-09-14 | 华南农业大学 | A kind of detection of log board hole defect and localization method based on ellipse fitting |
| CN109461044A (en) * | 2018-09-21 | 2019-03-12 | 南京林业大学 | Customize the mistake proofing checking method and its device of the board-like part processing hole location of household |
| CN110390696A (en) * | 2019-07-03 | 2019-10-29 | 浙江大学 | A kind of circular hole pose visible detection method based on image super-resolution rebuilding |
| CN111896221A (en) * | 2020-07-30 | 2020-11-06 | 四川大学 | Alignment method of rotating optical measurement system for virtual coordinate system auxiliary camera calibration |
| CN112001917A (en) * | 2020-09-04 | 2020-11-27 | 南京大学金陵学院 | Machine vision-based geometric tolerance detection method for circular perforated part |
Non-Patent Citations (2)
| Title |
|---|
| 唐盼盼;: "基于激光VR虚拟现实技术的精密零件外观设计研究", 自动化与仪器仪表, no. 04 * |
| 李海国: "瓦座孔位置度超差的修正", 《机械工程师》, pages 32 - 33 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113379688B (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021213223A1 (en) | Weld quality inspection method, apparatus and system, and electronic device | |
| DE102006040365A1 (en) | System and method for evaluating a machined surface of a metal casting component | |
| CN106226325A (en) | A kind of seat surface defect detecting system based on machine vision and method thereof | |
| KR101995396B1 (en) | Method and system for detecting defect in produnt | |
| CN115392512B (en) | Equipment maintenance method and system based on AR technology and related equipment | |
| CN109358067A (en) | Motor ring varistor defect detecting system based on computer vision and method | |
| CN116805311B (en) | Automobile part surface defect monitoring method based on robot vision | |
| CN115144399B (en) | Assembly quality detection method and device based on machine vision | |
| CN109813728A (en) | A kind of circuit board solder joint detection method and system | |
| CN110954555A (en) | WDT 3D vision detection system | |
| CN111127335A (en) | Bolt installation verticality head-up shooting visual detection method | |
| CA2464033A1 (en) | Inspection system and method | |
| KR20170080910A (en) | 3d shape inspection system | |
| CN113379688A (en) | Stabilizer bar hole deviation detection method and system based on image recognition | |
| CN112536643B (en) | Machine health monitoring method and device and computer readable storage medium | |
| EP2679339A3 (en) | Device for imaging and monitoring a milling profile and method for determining correction values for tool positions in a milling process | |
| WO2000028309A1 (en) | Method for inspecting inferiority in shape | |
| CN116258838A (en) | Intelligent visual guiding method for duct piece mold clamping system | |
| CN113433129B (en) | Six-axis robot deburring cutter detection mechanism and method thereof | |
| CN112665885A (en) | Stability evaluation method and device for hoisting equipment, hoisting equipment and storage medium | |
| CN112837285B (en) | Edge detection method and device for panel image | |
| KR102435468B1 (en) | Vehicle body assembly hole processing system using vision sensor | |
| CN111562768A (en) | Parallel multi-channel numerical control machine tool | |
| CN110455809A (en) | A kind of machine vision detection device and method of rod surface defect | |
| CN114152457B (en) | Method for improving monitoring capability of precise servo turntable and precise servo turntable |
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 |