CN113379688B - 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
- CN113379688B CN113379688B CN202110596698.8A CN202110596698A CN113379688B CN 113379688 B CN113379688 B CN 113379688B CN 202110596698 A CN202110596698 A CN 202110596698A CN 113379688 B CN113379688 B CN 113379688B
- Authority
- CN
- China
- Prior art keywords
- information
- virtual
- circle center
- hole
- center position
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000003381 stabilizer Substances 0.000 title claims abstract description 68
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 230000009467 reduction Effects 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 29
- 238000012958 reprocessing Methods 0.000 claims description 19
- 238000005070 sampling Methods 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 3
- 230000000087 stabilizing effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 8
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 238000005282 brightening Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
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 application belongs to the field of workpiece detection, and provides a stabilizer bar hole deviation detection method and system based on image recognition, aiming at the problem that judgment is difficult when a positioning hole is deviated 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 the basic image information to obtain intermediate image information, wherein the preprocessing comprises noise reduction and deburring; obtaining virtual circle center position information and virtual radius information of the positioning hole according to the intermediate image information; and judging whether the positioning hole deviates according to the virtual circle center position information and the preset standard circle center position information, and obtaining 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 application 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 automobile stabilizer bar device is arranged between the auxiliary frame and the suspension of the automobile and used for balancing the automobile body and preventing the automobile body from excessively and laterally rolling when turning. A common automobile stabilizer bar device adopts a stabilizer bar connecting rod to connect a stabilizer bar body with a pillar 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 ends of the stabilizer bar, one middle section 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 locating holes are used for limiting bevel gear members sleeved at two ends of the stabilizer bar. Whether the positioning hole is offset affects the connection of the whole stabilizer bar with the whole vehicle and the stability of the whole vehicle body when the vehicle runs. For this reason, how to judge whether the positioning hole of the stabilizer bar deviates from the preset position at the time of manufacture and whether the periphery of the positioning hole is smooth or not is an important part in the quality evaluation of the stabilizer bar.
Disclosure of Invention
The application provides a stabilizer bar hole deviation detection method and system based on image recognition, which solve the problems of difficult judgment and inaccurate judgment when a positioning hole is recognized to deviate by naked eyes in the prior art.
The basic scheme provided by the application 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 the basic image information to obtain intermediate image information, wherein the preprocessing comprises noise reduction and deburring;
obtaining virtual circle center position information and virtual radius information of the positioning hole according to the intermediate image information;
judging whether the positioning hole deviates according to the virtual circle center position information and the preset standard circle center position information, and obtaining 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 circumference information according to the virtual circle center position information and the virtual radius information;
calculating the pixel ratio of the basic image information and the virtual hole circumference information according to the virtual hole circumference information and the basic image information;
and judging whether the positioning hole is bad according to the pixel ratio, and obtaining hole circumference judging information, wherein the hole circumference judging information is that the positioning hole is bad or good.
The beneficial effects are that: in the scheme, noise reduction and burr removal are carried out on the basic image information through preprocessing, so that the subsequent determination of the virtual circle center position is convenient, and the accuracy of the determination of the virtual circle center position is improved. Then, the virtual circle center is close to the real circle center by referring to the information points of most edges in the intermediate image information, and 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 the position comparison between the virtual circle center and the standard circle center, so that whether the whole positioning hole is deviated 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 are fully realized, and the faults caused by manual naked eye observation are avoided.
The virtual hole circumference information is a set of all pixel points on a virtual circle drawn by taking the virtual circle center position as the circle center and virtual radius information as the radius; calculating the proportion of the number of overlapped pixels in the two pixel point sets of the virtual hole periphery information and the basic hole periphery information to the number of all pixels, and taking the proportion as the pixel ratio of the superposition of the basic image information and the virtual hole periphery information; the higher the pixel ratio is, the higher the coincidence between the basic image information and the virtual hole circumference information is proved, that is, the more the edge of the positioning hole corresponding to the basic image information approaches to a perfect circle, the hole circumference judgment information is set as positioning Kong Lianghao; correspondingly, the lower the pixel ratio, the lower the coincidence between the basic image information and the virtual hole circumference information is proved, the Kong Zhoubu of the positioning hole corresponding to the basic image information tends to be a perfect circle, and the hole circumference judgment information is set to be the positioning Kong Buliang. According to the scheme, whether the edge of the positioning hole is poor or not is automatically judged, burrs and gaps of the positioning hole can be clearly judged, and compared with manual naked eye identification, the accuracy is higher.
Further, 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 circumference information according to the virtual hole circumference 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 processed or the workpiece cannot be reprocessed.
The beneficial effects are that: on the basis of the scheme, calculating the pixel deviation degree between the basic image information and the virtual hole circumference information; pixels in the basic image information and pixels in the virtual hole periphery information are in one-to-one correspondence, the pixels in the basic image information correspond to the pixels in the unique virtual hole periphery information, the pixels in the virtual hole periphery information also correspond to the 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), and therefore the sum of the distances between the pixels in the basic image information and the pixels in the virtual hole periphery information which are mutually corresponding to each other is minimum.
When the corresponding pixel in the basic image information is located between the pixel in the virtual hole Zhou Xinxi and the pixel between the virtual circle center, the distance between the pixel in the basic image information and the pixel in the virtual hole circumference information is set to be a positive number; otherwise, negative numbers. The foregoing distance is set as the pixel deviation degree. And then, according to the pixel deviation degree, obtaining the workpiece reprocessing feasibility information, 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, judging that the workpiece is workable, namely, the workpiece reprocessing feasibility information is that the workpiece can be processed; otherwise, the workpiece is set to be capable of being processed again in the processing feasibility information.
Further, the stable dry hole deviation detection method further comprises the following steps:
when the hole circumference determination information is the positioning Kong Buliang,
and executing 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.
The beneficial effects are that: in the scheme, the subsequent workpiece processing feasibility judgment is carried out only when the hole circumference judgment information is the positioning Kong Buliang, so that 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.
Further, the obtaining the virtual center position information and the virtual radius information of the positioning hole according to the intermediate image information specifically includes:
detecting an image edge from the intermediate image information, and grabbing a sampling point;
calculating the current circle center virtual position of each group by taking three sampling points as a group;
according to all the current virtual positions of the circle centers, virtual circle center position information is summarized;
and calculating an average value between the virtual circle center position information and the distance between each sampling point, and calculating virtual radius information.
Further, the step of summarizing virtual circle center position information according to all the current circle center virtual positions includes:
and screening out the current circle center virtual positions with the shortest distance from the other current circle center virtual positions from all the current circle center virtual positions as virtual circle center position information.
Further, the step of summarizing 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 the current circle center virtual positions is shortest.
Further, the step of summarizing virtual circle center position information according to all the current circle center virtual positions includes:
the virtual circle center position information is set so as to ensure that the sum of square differences between every two virtual circle center positions is minimum.
The application also provides a stabilizer bar hole deviation detection system based on image recognition, which comprises:
the limiting module is used for limiting the space position of the stabilizer bar;
the image acquisition module is used for acquiring basic image information of positioning holes at two ends of the stabilizing rod 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 circumference 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 virtual circle center position information and 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 the 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 circumference determination information according to the virtual circle center position information and preset standard circle center position information, where the hole circumference determination information is that the positioning hole is bad or 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 processed or the workpiece 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 application;
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 application;
FIG. 3 is a schematic structural view of the limit 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 a further detailed description of the embodiments:
for the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the following detailed description of the embodiments of the present application will be given with reference to the accompanying drawings. However, those of ordinary skill in the art will understand that in various embodiments of the present application, numerous technical details have been set forth in order to provide a better understanding of the present application. However, the claimed application may be practiced without these specific details and with various changes and modifications based on the following embodiments.
First embodiment:
the first embodiment of the application 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 the basic image information to obtain intermediate image information, wherein the preprocessing comprises noise reduction and deburring; obtaining virtual circle center position information and virtual radius information of the positioning hole according to the intermediate image information; and judging whether the positioning hole deviates according to the virtual circle center position information and the preset standard circle center position information, and obtaining positioning hole judgment information, wherein the positioning hole judgment information is that the positioning hole deviates or the positioning hole does not deviate.
Noise reduction and burr removal are carried out on the basic image information 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 close to the real circle center by referring to the information points of most edges in the intermediate image information, and 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 the position comparison between the virtual circle center and the standard circle center, so that whether the whole positioning hole is deviated 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 are fully realized, and the faults caused by manual naked eye observation are avoided.
The implementation details of the stabilizer bar hole deviation detection method based on image recognition are specifically described below, and the following is only implementation details provided for convenience of understanding, but is not necessary to implement the present embodiment, and the 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.
S1, acquiring basic image information of positioning holes at two ends of the fixed stabilizer bar.
Specifically, the fixing of the stabilizer bar is realized by a limiting module in the stabilizer bar hole deviation detection system based on image recognition (the shape structure of the limiting module is shown in fig. 3), and the fixed stabilizer bar is spatially limited and cannot easily move. The implementation of step S1 is: the image acquisition modules are arranged near the positioning holes at the two ends of the stabilizer bar and are used for acquiring images of areas where the positioning holes are located, and the images are set as basic image information. Therefore, each positioning hole in the two positioning holes of the fixed rod corresponds to unique basic image information.
S2, preprocessing the basic image information to obtain intermediate-level image information, wherein the preprocessing comprises noise reduction and deburring.
Specifically, the basic image information is preprocessed, so that subsequent image recognition is facilitated, and the image of the positioning Kong Kongzhou in the basic image information is clear. The pretreatment process comprises noise reduction, deburring or brightening.
The process of improving the brightness of the basic image information comprises the steps of acquiring gray data of each pixel in the basic image information; calculating average gray values of a plurality of pixel points at the central position in the basic image information; calculating a parameter value of a preset parameter according to a first formula, wherein the first formula is gamma=log (Ga) -1, ga is the average gray value, and gamma is the preset 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 information Gamma And the brightness value of any color channel of any pixel point after adjustment is obtained. However, the processes of noise reduction and deburring of the basic image information have been widely used by image editing software, such as a beautiful image and a beautiful image, and the method of noise reduction and deburring is not modified in the scheme, so that the applicant does not describe the process too much. Therefore, the method for realizing noise reduction and deburring in the step can be to adopt a microprocessor, and the microprocessor is loaded with noise reduction and deburring image editing software.
And S3, obtaining virtual circle center position information and virtual radius information of the positioning hole according to the intermediate image information.
Specifically, detecting an image edge from the intermediate image information, and grabbing a sampling point; calculating the current circle center virtual position of each group by taking three sampling points as a group; according to all the current virtual positions of the circle centers, virtual circle center position information is summarized; and calculating an average value between the virtual circle center position information and the distance between each sampling point, and calculating virtual radius information.
The specific method comprises the following steps of:
first, the current circle center virtual position with the shortest distance from other current circle center virtual positions is screened out from all the current circle center virtual positions and is used as virtual circle center position information. The method essentially screens out a current circle center virtual position meeting the requirement from among all current circle center virtual positions, and the screening condition is that the sum of distances from the current circle center virtual position to other current circle center virtual positions is shortest.
Secondly, setting virtual circle center position information to ensure that the distance between the virtual circle center position information and all the 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 from the virtual circle center position information to all current circle center virtual positions is shortest, and the virtual circle center position can correspond to the center of a positioning hole as far as possible.
Thirdly, setting virtual circle center position information to ensure that the sum of square differences between every two virtual circle center position information and all current circle center virtual positions is minimum.
And S4, judging whether the positioning hole deviates according to the virtual circle center position information and the preset standard circle center position information, and obtaining positioning hole judgment information, wherein the positioning hole judgment information is that the positioning hole deviates or the positioning hole does not deviate.
Specifically, the formulation of the virtual circle center position information refers to information points of most edges in the intermediate image information, the virtual circle center position information is very close to the real circle center, and the deviation degree (such as the distance between the virtual circle center and the standard circle center) between the virtual circle center position information and the standard circle center position information is known through the position comparison between the virtual circle center position information and the standard circle center position information, so that whether the whole positioning hole is deviated 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 does not change during operation.
In the implementation stage, a standard deviation distance k is usually set, the actual distance from the virtual circle center position information to 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 d value is, the larger the deviation is; when d.gtoreq.k, it is determined that the current deviation distance d has exceeded the predetermined standard deviation distance k, that is, the degree of deviation has exceeded the allowable error range, and the positioning hole determination information is set as the positioning hole deviation. Otherwise, the positioning hole judgment information is set so that the positioning hole does not deviate.
And S5, after the execution of the step S3 is completed, obtaining virtual hole circumference information according to the virtual circle center position information and the virtual radius information.
Specifically, a virtual circle is drawn by using the virtual circle center position calculated in S3 as a circle center and the virtual radius information as a radius, and a set of all pixels on the virtual circle is defined as a virtual hole Zhou Xinxi.
S6, calculating the pixel ratio of the basic image information and the virtual hole circumference information according to the virtual hole circumference information and the basic image information.
Specifically, on the basis of the completion of the execution of step S5, calculating the proportion of the number of the pixels which can be overlapped in the two pixel point sets, namely the virtual hole periphery information and the basic hole periphery information, to the number of all the pixels, and taking the proportion as the pixel ratio of the superposition of the basic image information and the virtual hole periphery information; the higher the pixel ratio is, the higher the coincidence between the basic image information and the virtual hole circumference information is proved, that is, the more the edge of the positioning hole corresponding to the basic image information approaches to a perfect circle, the hole circumference judgment information is set as positioning Kong Lianghao; correspondingly, the lower the pixel ratio, the lower the coincidence between the basic image information and the virtual hole circumference information is proved, the Kong Zhoubu of the positioning hole corresponding to the basic image information tends to be a perfect circle, and the hole circumference judgment information is set to be the positioning Kong Buliang.
S7, calculating pixel deviation 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 processed or the workpiece cannot be reprocessed.
Specifically, on the basis of completion of the aforementioned step S5, the pixel deviation m between the basic 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 and pixels in the virtual hole periphery information are in one-to-one correspondence, the pixels in the basic image information correspond to the pixels in the unique virtual hole periphery information, the pixels in the virtual hole periphery information also correspond to the 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), and therefore the sum of the distances between the pixels in the basic image information and the pixels in the virtual hole periphery information which are mutually corresponding to each other is minimum. When the corresponding pixel in the basic image information is located between the pixel in the virtual hole Zhou Xinxi and the pixel between the virtual circle center, the distance between the pixel in the basic image information and the pixel in the virtual hole circumference information is set to be a positive number; otherwise, negative numbers. The foregoing distance is set as the pixel deviation m.
And then, according to the pixel deviation m, obtaining the workpiece reprocessing feasibility information, 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, judging that the workpiece is workable, namely, the workpiece reprocessing feasibility information is that the workpiece can be processed; otherwise, the workpiece is set to be capable of being processed again in the processing feasibility information.
In some embodiments, after steps S5 and S6 are performed, step S7 is performed according to the content of the hole circumference determination information in S6, specifically: and when the hole circumference judging information is positioning Kong Buliang, performing the calculation of 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 workpiece processing feasibility judgment is performed only when the hole circumference judgment information is the positioning Kong Buliang, so that 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.
Second embodiment:
the second embodiment of the present application further provides a stabilizer bar hole deviation detection system based on image recognition, as shown in fig. 2, including:
a limiting module 21 for limiting the 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 stabilizing rod 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 perform a stabilizer bar hole deviation detection method based on image recognition according to any one of the above first embodiment, and send hole deviation detection result information to an output module; the hole deviation detection result information comprises at least one of positioning hole judgment information, hole circumference judgment information and workpiece reprocessing feasibility information;
and an output module 24, 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 base image information to obtain intermediate image information;
the second image processing unit 232 is configured to obtain virtual center position information and virtual radius information of the positioning hole according to the intermediate image information; obtaining hole deviation detection result information according to the virtual circle center position information and the virtual radius information, wherein the hole deviation detection result information specifically comprises:
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;
and/or, according to the virtual circle center position information and the preset standard circle center position information, obtaining hole circumference judgment information, wherein the hole circumference judgment information is poor positioning holes or good positioning holes;
and/or calculating a pixel deviation between the base image information and the virtual hole circumference 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 processed or the workpiece cannot be reprocessed.
In a specific implementation stage, the limit module 21 is implemented by using a device shown in fig. 3, where the device includes two main supports 212 and two auxiliary supports 213 mounted on the workbench 211, one main support 212, two auxiliary supports 213 are located at two ends of the main support 212, the two auxiliary supports 213 have the same shape and structure, and the two auxiliary supports 213 are oppositely disposed with the main support 212 as a center. The main support 212 includes two support columns 2121 and a clamping member 2122, the clamping member 2122 is located between the two support columns 2121, the upper end faces of the two ends of the clamping member 2122 are respectively provided with a first limit groove, the upper end faces of the two support columns are respectively provided with a second limit groove and a third limit groove, and the inner walls of the first limit groove, the second limit groove and the third limit groove are matched with the surfaces of the middle part of the standard stabilizer bar 3. The top end of the auxiliary support 213 is provided with seating grooves, which are engaged with the surfaces of both ends of the standard stabilizer bar 3. Thus, the entire stabilizer bar may be restrained by the device shown in fig. 3.
The image acquisition module 22 may be implemented by using an infrared camera to acquire images of positioning holes at two ends of the stabilizer bar, for example, the infrared camera is mounted at the top end of the auxiliary supporting member 213 in the limiting module 21 shown in fig. 3, so that images of positioning holes at two ends of the stabilizer bar can be acquired; when the locating holes at the two ends of the stabilizer bar are shielded by the arrangement groove of the auxiliary supporting piece 213 when being limited by the limiting module 21, the infrared camera can be even arranged in the groove on the inner wall of the arrangement groove, so that the image acquisition of the area where the locating holes at the two ends of the stabilizer bar are located is realized.
The display module 25 is generally implemented by a display screen, and displays basic image information sent by the image acquisition module 22 where two infrared cameras are located simultaneously according to the positions of the infrared cameras during display. That is, the display module 25 simultaneously displays the basic image information transmitted from the two image pickup modules 22, the basic image information transmitted from the image pickup module 22 on the left side is displayed on the left side portion of the screen, and the basic image information transmitted from the image pickup module 22 on the right side is displayed on the right side portion of the screen.
The image processing module 23 is usually executed by a microprocessor, and the microprocessor is loaded with a program capable of implementing all the stabilizer bar hole deviation detection methods based on image recognition in the first embodiment, and executes the program, so that the corresponding first image processing unit 231 and the second processing unit 232 are part of the program. Alternatively, the image processing module 23 generally adopts a PCB board, on which two microprocessors are disposed, the first microprocessor is configured to load the function corresponding to the first image processing unit 231, and the second microprocessor is configured to load the function corresponding to the second image processing unit 232. The process of obtaining the locating hole judgment information by the function of the second image processing unit 232 loaded by the second microprocessor and the process of processing the intermediate-level image information sent by the first microprocessor is shown in fig. 4, and is specifically as follows: firstly, numbering each medium-level image information, wherein each medium-level image information corresponds to one number, and finishing all medium-level image information; 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 coordinate points in fig. 4; then, calculating virtual center position information (not shown in fig. 4) and virtual radius information of a plurality of groups of positioning holes according to the position information of the sampling points, wherein the virtual radius information corresponds to the distance from the center to the edge of the holes in fig. 4; then, comprehensively calculating the distances among the virtual circle center position information of the plurality of groups of positioning holes to obtain the whole virtual circle center position information; finally, calculating the distance between the whole virtual circle center position information and the preset standard circle center position information (the distance between circle centers in the corresponding figure 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.
The output module 24 is usually a data interface with physical properties, so as to output the hole deviation detection result information; or a wireless antenna is adopted to send the hole deviation detection result information to related management personnel and the like through a wireless network/a wired network.
It is to be noted that, in this embodiment, the system is an example corresponding to the first embodiment, and this embodiment may be implemented in cooperation with the first embodiment, so that in order to reduce repetition, a description is omitted here. Accordingly, the related art details mentioned in the present embodiment can also be applied to the first embodiment.
It should be noted that each unit referred to in this embodiment is a logic unit, and in practical application, one logic unit may be one physical unit, or may be a part of one physical unit, or may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present application, units that are not so close to solving the technical problem presented by the present application are not introduced in the present embodiment, but this does not indicate that other units are not present in the present embodiment.
The foregoing is merely an embodiment of the present application, and a specific structure and characteristics of common knowledge in the art, which are well known in the scheme, are not described herein, so that a person of ordinary skill in the art knows all the prior art in the application date or before the priority date, can know all the prior art in the field, and has the capability of applying the conventional experimental means before the date, and a person of ordinary skill in the art can complete and implement the present embodiment in combination with his own capability in the light of the present application, and some typical known structures or known methods should not be an obstacle for a person of ordinary skill in the art to implement the present application. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present application, and these should also be considered as the scope of the present application, which does not affect the effect of the implementation of the present application and the utility of the patent. The protection scope of the present application is subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (8)
1. The stabilizer bar hole deviation detection method based on image recognition is characterized by comprising the following steps of:
acquiring basic image information of positioning holes at two ends of the fixed stabilizer bar;
preprocessing the basic image information to obtain intermediate image information, wherein the preprocessing comprises noise reduction and deburring;
obtaining virtual circle center position information and virtual radius information of the positioning hole according to the intermediate image information;
judging whether the positioning hole deviates according to the virtual circle center position information and the preset standard circle center position information, and obtaining 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 circumference information according to the virtual circle center position information and the virtual radius information;
calculating the pixel ratio of the basic image information and the virtual hole circumference information according to the virtual hole circumference information and the basic image information;
judging whether the positioning holes are bad according to the pixel ratio, and obtaining hole circumference judging information, wherein the hole circumference judging information is that the positioning holes are bad or good;
the method for obtaining the virtual circle center position information and the virtual radius information of the positioning hole according to the intermediate image information specifically comprises the following steps:
detecting an image edge from the intermediate image information, and grabbing a sampling point;
calculating the current circle center virtual position of each group by taking three sampling points as a group;
according to all the current virtual positions of the circle centers, virtual circle center position information is summarized;
and calculating an average value between the virtual circle center position information and the distance between each sampling point, and calculating virtual radius information.
2. The stabilizer bar hole deviation detection method based on image recognition according to claim 1, wherein the method comprises the following steps: the method for detecting the hole deviation of the stabilizer bar further comprises the following steps:
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;
and 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.
3. The method for detecting the hole deviation of the stabilizer bar based on the image recognition according to claim 2, wherein the method for detecting the hole deviation of the stabilizer bar further comprises the following steps:
when the hole circumference determination information is the positioning Kong Buliang,
and executing 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 for detecting hole deviation of stabilizer bar based on image recognition according to claim 1, wherein the step of generalizing virtual circle center position information according to all current circle center virtual positions comprises the steps of:
and screening out the current circle center virtual positions with the shortest distance from the other current circle center virtual positions from all the current circle center virtual positions as virtual circle center position information.
5. The method for detecting hole deviation of stabilizer bar based on image recognition according to claim 1, wherein the step of generalizing virtual circle center position information according to all current circle center virtual positions comprises the steps of:
and setting virtual circle center position information to ensure that the distance between the virtual circle center position information and all the current circle center virtual positions is shortest.
6. The method for detecting hole deviation of stabilizer bar based on image recognition according to claim 1, wherein the step of generalizing virtual circle center position information according to all current circle center virtual positions comprises the steps of:
the virtual circle center position information is set so as to ensure that the sum of square differences between every two virtual circle center positions is minimum.
7. Stabilizer bar hole deviation detecting system based on image recognition, characterized by comprising:
the limiting module is used for limiting the space position of the stabilizer bar;
the image acquisition module is used for acquiring basic image information of positioning holes at two ends of the stabilizing rod 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 according to any one of claims 1-6 and outputting hole deviation detection result information; the hole deviation detection result information comprises at least one of positioning hole judgment information, hole circumference judgment information and workpiece reprocessing feasibility information.
8. The stabilizer bar hole deviation detecting system based on image recognition according to claim 7, 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 virtual circle center position information and 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 the 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 CN113379688A (en) | 2021-09-10 |
| CN113379688B true 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 |
|---|
| 基于激光VR虚拟现实技术的精密零件外观设计研究;唐盼盼;;自动化与仪器仪表(04);全文 * |
| 瓦座孔位置度超差的修正;李海国;《机械工程师》;32-33 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113379688A (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109520706B (en) | Screw hole coordinate extraction method of automobile fuse box | |
| EP1848961B1 (en) | Method for calibrating a measuring system | |
| JP4803450B2 (en) | On-vehicle camera calibration device and vehicle production method using the device | |
| DE10393821B4 (en) | Method and system for measuring caster | |
| CN107036530A (en) | The calibration system and method for the location of workpiece | |
| CN112767338A (en) | Assembled bridge prefabricated part hoisting and positioning system and method based on binocular vision | |
| CN108927805A (en) | A kind of robot automation's plug pin method of view-based access control model compensation | |
| CN115880296B (en) | Machine vision-based prefabricated part quality detection method and device | |
| CN113379688B (en) | Stabilizer bar hole deviation detection method and system based on image recognition | |
| CN113752086A (en) | Method and device for detecting state of numerical control machine tool cutter | |
| CN111210392B (en) | Hub valve hole positioning method based on digital image processing | |
| CN110954555A (en) | WDT 3D vision detection system | |
| CN112665885B (en) | Stability evaluation method and device for hoisting equipment, hoisting equipment and storage medium | |
| CN111644814B (en) | Wind power rotor machining method | |
| CN114299260A (en) | AR (augmented reality) -glasses-based product accessory detection, positioning, guiding and assembling method and system | |
| CN112164018B (en) | Machine vision calibration system and calibration method thereof | |
| CN111571276A (en) | Numerical control machine tool capable of identifying workpiece and automatically inputting technological parameters and machining method thereof | |
| CN117036360B (en) | Screw visual positioning method and system based on image analysis | |
| JP5590387B2 (en) | Color target position determination device | |
| CN116834023B (en) | Nailing robot control system | |
| CN115854881A (en) | C-shaped hook balance detection method, device and system, electronic equipment and storage medium | |
| CN114353702A (en) | Rotary opening adjusting area measuring device based on visual detection | |
| WO2022210006A1 (en) | Information processing system | |
| CN116907366B (en) | Screw locking degree detecting system | |
| CN110587379B (en) | Hole probing method of flow drill screwing equipment |
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 |