CN204009938U - The recognition system of wheel hub type - Google Patents
The recognition system of wheel hub type Download PDFInfo
- Publication number
- CN204009938U CN204009938U CN201420166708.XU CN201420166708U CN204009938U CN 204009938 U CN204009938 U CN 204009938U CN 201420166708 U CN201420166708 U CN 201420166708U CN 204009938 U CN204009938 U CN 204009938U
- Authority
- CN
- China
- Prior art keywords
- wheel hub
- recognition system
- production line
- processing apparatus
- image processing
- 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.)
- Expired - Fee Related
Links
Abstract
The utility model provides a kind of recognition system of wheel hub type, it comprises production line and support, support is comprised of two identical tripod and crossbeams of vertically placing, the two ends of its middle cross beam are connected with two tops of two tripods respectively, production-line arrangement is between two tripods, on the roller of production line, be provided with the trigger sensor of taking pictures, at the centre position place of crossbeam, be fixed with camera, this recognition system also comprises and is positioned at the image processing apparatus of support side and the display panel being connected with the upper surface of image processing apparatus.Native system has been avoided the problem of the misjudgement erroneous judgement of traditional vision detection system, has greatly improved the work efficiency of wheel hub detection production line.
Description
Technical field
The utility model relates to a kind of recognition system, relates to particularly a kind of recognition system of wheel hub type.
Background technology
Along with the fast development of automobile industry, the demand that realizes various productions by robotization is also in corresponding increase.The kind of automotive hub is more and more various.And the wheel hub that carries out the various models of nondestructive examination detection on hub production line is all the discharge that mixes very much, the detected parameters corresponding to wheel hub of each model of working together is all different, therefore for miscellaneous wheel hub, carries out Classification and Identification more and more important.The earliest, mainly by artificial observation, carry out discriminator, inefficiency not only, and because long observation can make visual fatigue cause classification error, Hui Gei enterprise produces and causes immeasurable loss, there is afterwards relevant vision-based detection research, but this type of pick-up unit of researching and proposing has just obtained wheel hub surface seldom, wheel hub information compare device there will be many erroneous judgements and misjudgement phenomenon when in the face of the dissimilar wheel hub of identification, the accuracy rate that identification is distinguished is not high, can not meet the Production requirement of factory.A kind ofly miscellaneous wheel hub Classification and Identification system out can be seemed to particularly important.
Summary of the invention
In order to solve the problems of the technologies described above, the utility model provides a kind of recognition system of wheel hub type, it comprises production line and support, on production line, be placed with wheel hub, support is comprised of two identical tripod and crossbeams of vertically placing, the two ends of its middle cross beam are connected with two tops of two tripods respectively, thereby crossbeam is paralleled with ground, production-line arrangement is between two tripods and adopt roller type structure, on the roller of production line, be provided with the trigger sensor of taking pictures, place, centre position at crossbeam is fixed with camera, between camera and crossbeam, adopt ring-type fastening device structure to be connected, this recognition system also comprises and is positioned at the image processing apparatus of support side and the display panel being connected with the upper surface of image processing apparatus, on display panel, be provided with button.
Preferably, described camera is CCD industrial camera.
Preferably, described image processing apparatus is industrial computer.
By adopting native system, can in the identification process of wheel hub type, save a large amount of human and material resources, can also image processing apparatus be extracted by wheel hub feature simultaneously, enable to identify from miscellaneous wheel hub and belong to which kind when front hub, avoid the problem of the misjudgement erroneous judgement of traditional vision detection system, greatly improved the work efficiency of wheel hub detection production line.
Accompanying drawing explanation
Fig. 1 is according to the structural representation of the recognition system of the wheel hub type of an exemplary embodiment in the utility model.
Embodiment
In 1 pair of the utility model, a detailed exemplary embodiment is described below with reference to the accompanying drawings.
Fig. 1 shows a kind of recognition system of wheel hub type, it comprises for placing production line 1 and the support 2 of wheel hub 4, support 2 is comprised of two identical tripod 7 and crossbeams 8 of vertically placing, the two ends of its middle cross beam 8 are connected with two tops of two tripods 7 respectively, thereby crossbeam 8 is paralleled with ground, production line 1 is arranged between two tripods 7 and adopts roller type structure for the transmission of wheel hub, on the roller of production line 1, be provided with the trigger sensor of taking pictures, in addition, place, centre position at crossbeam 8 is fixed with camera 2, between camera 2 and crossbeam 8, adopt ring-type fastening device structure to be connected, camera 2 can move left and right on crossbeam 8 like this, conveniently in debugging, find best shooting point, this recognition system also comprises and is positioned at the image processing apparatus 5 of support 2 sides and the display panel 6 being connected with image processing apparatus 5 upper surfaces, on display panel 8, be provided with button, for the switching of picture or the processing of emergency condition, operate like this, wherein, this camera 2 can be CCD industrial camera, image processing apparatus 5 can be industrial computer.
By adopting this wheel hub identification system based on vision of the present utility model, can save a large amount of manpowers and material resources, also system can be at the motion flow that there is no to complete in manually-operated situation a whole set of wheel hub identification.
Adopt the recognition system of above-mentioned wheel hub type to the type of wheel hub, to identify by the following method: the picture that is first captured in 3 wheel hubs that transmit 4 on production line by being fixed on camera 2 on the crossbeam 8 of support 1, then the pictorial information collecting is passed to image processing apparatus 5 by wired or wireless mode, main being responsible for of image processing apparatus 5 carried out pre-service to the picture collecting, comprising operations such as gray scale processing, value, denoisings, then the characteristic information of 5 pairs of wheel hubs of image processing apparatus extracts, particularly, graphics processing unit 5 is for having translation, rotation, 34 rank moment characteristics values that convergent-divergent is constant and wheel hub outline radius, center circle, the characteristic informations such as screw hole radius extract, better to express the detailed information of wheel hub, in addition, also for the axle bar number information of wheel hub, extract, wherein, the extracting mode of this characteristic information has improved the more single situation of vision detection system eigenwert in the past, extracted Hu invariant moment features amount, the outline radius of wheel hub, the information such as number of the radius of the screw hole of center circle and center circle periphery and axle bar, improved significantly the accuracy of identification hub type, misjudgement and erroneous judgement have been greatly reduced, improved production efficiency.After information extraction, the characteristic information of the new warehouse-in wheel hub that 5 pairs of graphics processing units extract is preserved, and directly the eigenwert of the feature database the inside of the eigenwert obtaining and preservation is compared, by comparison using obtain with feature database in immediate wheel hub classification as the classification under front hub, finally also testing result is shown by display panel 6 or tri coloured lantern, also can pass to PLC and carry out some follow-up actions.
To introduce the extracting method of above-mentioned eigenwert below:
First extracted not bending moment of the improved Hu with translation, convergent-divergent, invariable rotary.Concrete grammar is as follows:
According to the definition of Hu square: for gray-scale map f (x, y) expression the utility model for of the wheel hub gathering.P+q rank standard square under discrete state is:
P+q rank center matrix is:
Wherein
representative be the center of gravity of image, N, M is corresponding is respectively height and the width of the wheel hub picture that gathers.Normalized center square is:
By above formula can ask for Hu definition based on 2 rank and 3 rank 7 bending moments not, these 7 not the exponent number of bending moment lower for this detail section of wheel hub important feature can not completely describe.What therefore the utility model adopted on this basis is 3 features based on 4 rank, and formula is as follows:
φ
1＝η
40+η
13+η
22
φ
2＝(η
31-η
13)
2+5(η
40+η
04)
2
φ
3＝(η
31-3η
22+η
40)
2+12(η
31-η
13)
2
3 invariant moment features that extract by the method can also can identify any wheel hub in the situations such as wheel hub generation translation, convergent-divergent, rotation, only by this eigenwert, different classes of wheel hub can't be identified, the utility model also extracts the radius size of the screw hole of the large radius of circle of wheel hub, center circle and center circle periphery on this basis, then the number of axle bar has also been carried out to corresponding extraction.These feature extractions save as template library after well, then, in reality detects, these characteristic informations and the database that extract are compared, thereby which kind of wheel hub that obtains current detection belong to.
An exemplary embodiment of the present utility model has obtained detailed description with reference to accompanying drawing.These detailed descriptions further believe content only to those skilled in the art, for implementing preferred aspect of the present utility model, and can not limit scope of the present utility model.Only have the right requirement for determining protection domain of the present utility model.Therefore, the feature in aforementioned detailed description and the combination of step are dispensable implements the utility model in for the scope the broadest, and alternatively only the exemplary embodiment of special detailed description of the present utility model is provided to instruction.In addition, in order to obtain of the present utility model being attached with embodiment, in instructions, provide the various feature combination in several ways of instruction, yet these modes are not exemplified out especially.
Claims (3)
1. the recognition system of a wheel hub type, it comprises production line and support, on production line, be placed with wheel hub, support is comprised of two identical tripod and crossbeams of vertically placing, the two ends of its middle cross beam are connected with two tops of two tripods respectively, thereby crossbeam is paralleled with ground, production-line arrangement is between two tripods and adopt roller type structure, on the roller of production line, be provided with the trigger sensor of taking pictures, it is characterized in that: the place, centre position at crossbeam is fixed with camera, between camera and crossbeam, adopt ring-type fastening device structure to be connected, this recognition system also comprises and is positioned at the image processing apparatus of support side and the display panel being connected with the upper surface of image processing apparatus, on display panel, be provided with button.
2. the recognition system of wheel hub type as claimed in claim 1, is characterized in that: described camera is CCD industrial camera.
3. the recognition system of wheel hub type as claimed in claim 2, is characterized in that: described image processing apparatus is industrial computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420166708.XU CN204009938U (en) | 2014-04-09 | 2014-04-09 | The recognition system of wheel hub type |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420166708.XU CN204009938U (en) | 2014-04-09 | 2014-04-09 | The recognition system of wheel hub type |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN204009938U true CN204009938U (en) | 2014-12-10 |
Family
ID=52049909
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201420166708.XU Expired - Fee Related CN204009938U (en) | 2014-04-09 | 2014-04-09 | The recognition system of wheel hub type |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN204009938U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105059872A (en) * | 2015-08-28 | 2015-11-18 | 江苏天宏自动化科技有限公司 | Visual system for recognizing model of hub and deburring window |
| CN106382889A (en) * | 2016-11-17 | 2017-02-08 | 江苏天宏机械工业有限公司 | Wheel hub type identification and detection system |
| CN108491841A (en) * | 2018-03-21 | 2018-09-04 | 东南大学 | A kind of automotive hub type identification monitoring management system and method |
-
2014
- 2014-04-09 CN CN201420166708.XU patent/CN204009938U/en not_active Expired - Fee Related
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105059872A (en) * | 2015-08-28 | 2015-11-18 | 江苏天宏自动化科技有限公司 | Visual system for recognizing model of hub and deburring window |
| CN106382889A (en) * | 2016-11-17 | 2017-02-08 | 江苏天宏机械工业有限公司 | Wheel hub type identification and detection system |
| WO2018090567A1 (en) * | 2016-11-17 | 2018-05-24 | 江苏天宏机械工业有限公司 | System for identifying and detecting type of wheel hub |
| CN108491841A (en) * | 2018-03-21 | 2018-09-04 | 东南大学 | A kind of automotive hub type identification monitoring management system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4270355A3 (en) | Method for processing hazard reports from vehicles | |
| CN105551064B (en) | A kind of method based on characteristics of image estimation windrow volume change | |
| EP2838051A3 (en) | Linear road marking detection method and linear road marking detection apparatus | |
| Chang et al. | A mobile vision inspection system for tiny defect detection on smooth car-body surfaces based on deep ensemble learning | |
| EP3456597A3 (en) | Methods and systems for detecting weather conditions using vehicle onboard sensors | |
| CN111091546B (en) | Railway wagon coupler tail frame breaking fault identification method | |
| CN104331876A (en) | Line detection and image processing method and related devices thereof | |
| CN110910350B (en) | Nut loosening detection method for wind power tower cylinder | |
| CN106407924A (en) | Binocular road identifying and detecting method based on pavement characteristics | |
| CN107680091B (en) | Method for detecting falling defect of vibration damper of power transmission line | |
| CN101408985A (en) | Method and apparatus for extracting circular luminous spot second-pixel center | |
| CN102867195B (en) | Method for detecting and identifying a plurality of types of objects in remote sensing image | |
| CN103363893B (en) | A kind of red fuji apple size detection method | |
| CN102609938A (en) | Method for detecting vanishing points of road based on single image | |
| CN102930280A (en) | Method for identifying overhead high-voltage wire automatically from infrared image | |
| CN204009938U (en) | The recognition system of wheel hub type | |
| CN102789578A (en) | Infrared remote sensing image change detection method based on multi-source target characteristic support | |
| CN113379712A (en) | Steel bridge bolt disease detection method and system based on computer vision | |
| GB2598244A (en) | Systems and methods for automated detection of changes in extent of structures using imagery | |
| CN103914829B (en) | Method for detecting edge of noisy image | |
| CN105718964A (en) | Transmission line vibration damper visual detection method | |
| CN103245666A (en) | Automatic detecting method for appearance defects of storage battery polar plate | |
| CN104050674A (en) | Salient region detection method and device | |
| CN106408589A (en) | Vehicle-mounted overlooking camera based vehicle movement measurement method | |
| Cao et al. | Power line detection based on symmetric partial derivative distribution prior |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C56 | Change in the name or address of the patentee | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Qinhuai District of Nanjing city in Jiangsu province is 210000 Road No. 1 Patentee after: Nanjing aoyi Flight Control Technology Co. Ltd. Address before: Qinhuai District of Nanjing city in Jiangsu province is 210000 Road No. 1 Patentee before: Nanjing Aoyiweiteng Automation Technology Co., Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141210 Termination date: 20190409 |