CN109165649B - High-precision container hole detection method based on visual detection - Google Patents
High-precision container hole detection method based on visual detection Download PDFInfo
- Publication number
- CN109165649B CN109165649B CN201811023020.5A CN201811023020A CN109165649B CN 109165649 B CN109165649 B CN 109165649B CN 201811023020 A CN201811023020 A CN 201811023020A CN 109165649 B CN109165649 B CN 109165649B
- Authority
- CN
- China
- Prior art keywords
- screening
- box
- selecting
- holes
- candidate
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a high-precision detection method of container holes based on visual detection, which comprises the following steps: 1) manufacturing a standard template: 2) photographing the top of the container; 3) and (3) screening an optimal result: 3-1) primary screening: selecting a group of box holes with the maximum matching Score for length selection; selecting a certain number of candidate box holes from the ROI according to the Score and screening the candidate box holes according to the length; 3-1-3) if the step 3-1-1) fails, selecting a certain number of candidate box holes from the ROI, firstly selecting the candidate box holes according to the length, and then continuously screening by means of the box number position; 3-1-4) obtaining candidate box holes after preliminary screening; 3-2) screening the connecting lines of the common points in the candidate targets: 3-2-1) setting an angle deviation threshold value for screening; 3-2-2) if a plurality of box hole connecting lines meet the condition after the step 3-2-1), selecting the box hole with the higher Score; 3-3) obtaining the final screening result.
Description
Technical Field
The invention relates to an intelligent control technology, in particular to an intelligent control system for a container terminal, and particularly discloses a high-precision container hole detection method based on visual detection.
Background
Container hole detection is an important part of port automation, and container positioning can be realized through container hole detection.
At present, a visual identification technology is generally adopted in a container positioning method. Template matching is a common image identification method, but the traditional template matching algorithm is very easy to be interfered by external factors, the adaptability is not strong, and when the external environment is slightly changed, the robustness is greatly reduced, so that misjudgment is caused. In the practical application process, the container has the dirty and corrosive conditions, and certain influence is also generated on the matching of the templates.
Therefore, it is necessary to provide a method for accurately detecting the height of a container hole based on visual inspection to solve the above problems.
Disclosure of Invention
The invention aims to provide a high-precision detection method for container holes based on visual detection.
The technical scheme is as follows:
a high-precision detection method for container holes based on visual detection comprises the following steps:
1) manufacturing a standard template: matching is carried out by combining a scaling factor, a rotation factor and the like based on the inner and outer contour information of the box hole; setting a low threshold value to ensure that a plurality of candidate positions including the correct box hole position can be obtained, so as to facilitate subsequent screening;
2) photographing the top of the container;
3) and (3) screening an optimal result:
3-1) primary screening:
3-1-1) selecting a group of box holes which are matched with the Score to be the maximum for length selection;
3-1-2) selecting a certain number of candidate box holes from the ROI according to the Score and selecting the candidate box holes according to the length;
3-1-3) if the step 3-1-1) fails, selecting a certain number of candidate box holes from the ROI, firstly selecting the candidate box holes according to the length, and then continuously screening by means of the box number position;
3-1-4) obtaining candidate box holes after preliminary screening;
3-2) screening the connecting lines of the common points in the candidate targets:
3-2-1) setting an angle deviation threshold value for screening;
3-2-2) if a plurality of box hole connecting lines meet the condition after the step 3-2-1), selecting the box hole with the higher Score;
3-3) obtaining a final screening result:
3-3-1) the number of the box hole connecting lines is 0, and the positioning fails;
3-3-1) the number of the box hole connecting lines is 1, and the output result is obtained;
3-3-3) the number of the connecting lines of the box holes is more than 1, and if the positive direction of the container is from left to right, the first container is a high Score, the result is output; otherwise, searching a box hole connecting line which is close to the maximum Score connecting line of the first step and is high Score as an output result.
Compared with the prior art, the method has the advantages that the matching requirement is relaxed, and then the multiple candidate targets are secondarily screened, so that the positioning precision is effectively improved.
Drawings
FIG. 1 is the final result, including the template-matched ROI, the coordinates of the located left and right box holes and their connection information.
Detailed Description
Example (b):
referring to fig. 1, the present embodiment shows a method for detecting container holes based on visual inspection, which includes the following steps:
1) manufacturing a standard template: matching is carried out by combining a scaling factor, a rotation factor and the like based on the inner and outer contour information of the box hole; setting a low threshold value to ensure that a plurality of candidate positions including the correct box hole position can be obtained, so as to facilitate subsequent screening;
2) photographing the top of the container;
3) and (3) screening an optimal result:
3-1) primary screening:
3-1-1) selecting a group of box holes which are matched with the Score to be the maximum for length selection;
3-1-2) selecting a certain number of candidate box holes from the ROI according to the Score and selecting the candidate box holes according to the length;
3-1-3) if the step 3-1-1) fails, selecting a certain number of candidate box holes from the ROI, firstly selecting the candidate box holes according to the length, and then continuously screening by means of the box number position;
3-1-4) obtaining candidate box holes after preliminary screening;
3-2) screening the connecting lines of the common points in the candidate targets:
3-2-1) setting an angle deviation threshold value for screening;
3-2-2) if a plurality of box hole connecting lines meet the condition after the step 3-2-1), selecting the box hole with the higher Score;
3-3) obtaining a final screening result:
3-3-1) the number of the box hole connecting lines is 0, and the positioning fails;
3-3-2) the number of the box hole connecting lines is 1, and the output result is obtained;
3-3-3) the number of the connecting lines of the box holes is more than 1, and if the positive direction of the container is from left to right, the first container is a high Score, the result is output; otherwise, searching a box hole connecting line which is close to the maximum Score connecting line of the first step and is high Score as an output result.
Compared with the prior art, the method and the device have the advantages that the matching requirement is relaxed, and then the multiple candidate targets are subjected to secondary screening, so that the positioning accuracy is effectively improved.
What has been described above are merely some embodiments of the present invention. It will be apparent to those skilled in the art that various changes and modifications can be made without departing from the inventive concept thereof, and these changes and modifications can be made without departing from the spirit and scope of the invention.
Claims (1)
1. A high-precision detection method for container holes based on visual detection is characterized by comprising the following steps: the method comprises the following steps:
1) manufacturing a standard template: matching by combining a scaling factor and a rotation factor based on the inner and outer contour information of the box hole; setting a low threshold value to ensure that a plurality of candidate positions including the correct box hole position can be obtained, so as to facilitate subsequent screening;
2) photographing the top of the container;
3) and (3) screening an optimal result:
3-1) primary screening:
3-1-1) selecting a group of box holes which are matched with the Score to be the maximum for length selection;
3-1-2) selecting a certain number of candidate box holes from the ROI according to the Score and selecting the candidate box holes according to the length;
3-1-3) if the step 3-1-1) fails, selecting a certain number of candidate box holes from the ROI, firstly selecting the candidate box holes according to the length, and then continuously screening by means of the box number position;
3-1-4) obtaining candidate box holes after preliminary screening;
3-2) screening the connecting lines of the common points in the candidate targets:
3-2-1) setting an angle deviation threshold value for screening;
3-2-2) if a plurality of box hole connecting lines meet the condition after the step 3-2-1), selecting the box hole with the higher Score;
3-3) obtaining a final screening result:
3-3-1) the number of the box hole connecting lines is 0, and the positioning fails;
3-3-1) the number of the box hole connecting lines is 1, and the output result is obtained;
3-3-3) the number of the connecting lines of the box holes is more than 1, and if the positive direction of the container is from left to right, the first container is a high Score, the result is output; otherwise, searching a box hole connecting line which is close to the maximum Score connecting line of the first step and is high Score as an output result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811023020.5A CN109165649B (en) | 2018-09-03 | 2018-09-03 | High-precision container hole detection method based on visual detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811023020.5A CN109165649B (en) | 2018-09-03 | 2018-09-03 | High-precision container hole detection method based on visual detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109165649A CN109165649A (en) | 2019-01-08 |
| CN109165649B true CN109165649B (en) | 2022-04-15 |
Family
ID=64894017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811023020.5A Active CN109165649B (en) | 2018-09-03 | 2018-09-03 | High-precision container hole detection method based on visual detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109165649B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102024144A (en) * | 2010-11-23 | 2011-04-20 | 上海海事大学 | Container number identification method |
| CN102184398A (en) * | 2011-06-17 | 2011-09-14 | 电子科技大学 | Edge-detection-based container number positioning method |
| CN105930858A (en) * | 2016-04-06 | 2016-09-07 | 吴晓军 | Fast high-precision geometric template matching method enabling rotation and scaling functions |
| CN105956619A (en) * | 2016-04-27 | 2016-09-21 | 浙江工业大学 | Container lockhole coarse positioning and tracking method |
| CN106097329A (en) * | 2016-06-07 | 2016-11-09 | 浙江工业大学 | A kind of container profile localization method based on rim detection |
| CN108090895A (en) * | 2017-11-28 | 2018-05-29 | 浙江工业大学 | A kind of container lockhole contour extraction method based on image procossing |
-
2018
- 2018-09-03 CN CN201811023020.5A patent/CN109165649B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102024144A (en) * | 2010-11-23 | 2011-04-20 | 上海海事大学 | Container number identification method |
| CN102184398A (en) * | 2011-06-17 | 2011-09-14 | 电子科技大学 | Edge-detection-based container number positioning method |
| CN105930858A (en) * | 2016-04-06 | 2016-09-07 | 吴晓军 | Fast high-precision geometric template matching method enabling rotation and scaling functions |
| CN105956619A (en) * | 2016-04-27 | 2016-09-21 | 浙江工业大学 | Container lockhole coarse positioning and tracking method |
| CN106097329A (en) * | 2016-06-07 | 2016-11-09 | 浙江工业大学 | A kind of container profile localization method based on rim detection |
| CN108090895A (en) * | 2017-11-28 | 2018-05-29 | 浙江工业大学 | A kind of container lockhole contour extraction method based on image procossing |
Non-Patent Citations (2)
| Title |
|---|
| 基于双目立体视觉的集装箱识别与定位技术研究;马蕾;《中国优秀硕士学位论文全文数据库-息科技辑》;20131115(第11期);I138-769 * |
| 基于机器视觉的集装箱锁孔识别算法研究;宓为建 等;《中国工程机械学报》;20161031;第14卷(第5期);第399-402页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109165649A (en) | 2019-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR920004956B1 (en) | Drawing figure recognition apparatus | |
| JP2018522293A (en) | Visual identification method of multi-type BGA chip based on linear clustering | |
| CN107133623B (en) | Pointer position accurate detection method based on background difference and circle center positioning | |
| CN108133460B (en) | Color type state indicator identification method suitable for electric power robot | |
| CN105701492A (en) | Machine vision identification system and implementation method thereof | |
| CN107564006B (en) | Circular target detection method utilizing Hough transformation | |
| CN105654421A (en) | Projection transform image matching method based on transform invariant low-rank texture | |
| CN103049731A (en) | Decoding method for point-distributed color coding marks | |
| CN105991913B (en) | Method for positioning petal slot angle of camera module based on machine vision | |
| CN107507185B (en) | Method for rapidly detecting circle suitable for industrial detection | |
| CN109447062A (en) | Pointer-type gauges recognition methods based on crusing robot | |
| CN112085708B (en) | Method and equipment for detecting defects of straight line edges in outer contour of product | |
| CN115055964A (en) | Intelligent assembling method and system based on fuel injection pump | |
| CN111027530A (en) | Preprocessing method based on tire embossed character recognition | |
| CN109785324B (en) | Large-format PCB positioning method | |
| CN109165649B (en) | High-precision container hole detection method based on visual detection | |
| CN108520533B (en) | Workpiece positioning-oriented multi-dimensional feature registration method | |
| CN106503720B (en) | A kind of element image-recognizing method of removal suction nozzle interference | |
| CN111105418B (en) | High-precision image segmentation method for rectangular targets in image | |
| CN112418242B (en) | Color identification system suitable for large-scale targets and identification method thereof | |
| CN109034151A (en) | A kind of localization method for the identification of multiple pointer instruments | |
| CN111002376A (en) | Intelligent fool-proof method for PCB inner layer target hole | |
| CN114943710A (en) | Method for positioning circle center of thin-wall circular tube part by using improved least square fitting | |
| Meng et al. | A coarse-to-fine angle automatic correction method for glassivation passivation parts wafer | |
| KR102177329B1 (en) | Method for sensing of fiducial Mark |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230627 Address after: 215124 Unit G1-1002, Artificial Intelligence Industrial Park, No. 88, Jinji Lake Avenue, Suzhou Industrial Park, China (Jiangsu) Pilot Free Trade Zone, Suzhou, Jiangsu Province Patentee after: Suzhou Wuliang Intelligent Technology Co.,Ltd. Address before: 215300 Building 2, 271 Dongping Road, Baicheng Town, Kunshan City, Suzhou City, Jiangsu Province Patentee before: SUZHOU JU NENG IMAGE INSPECTION TECHNOLOGY Co.,Ltd. |