CN109590231A - A kind of non-regular shape material image measurement measuring and controlling device and method - Google Patents
A kind of non-regular shape material image measurement measuring and controlling device and method Download PDFInfo
- Publication number
- CN109590231A CN109590231A CN201811556787.4A CN201811556787A CN109590231A CN 109590231 A CN109590231 A CN 109590231A CN 201811556787 A CN201811556787 A CN 201811556787A CN 109590231 A CN109590231 A CN 109590231A
- Authority
- CN
- China
- Prior art keywords
- camera
- conveyer
- processing unit
- central processing
- laser
- 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.)
- Withdrawn
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/04—Sorting according to size
- B07C5/10—Sorting according to size measured by light-responsive means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind of non-regular shape material image measurement measuring and controlling device in image procossing and machine depth learning technology field and methods, described device includes conveyer and portal frame, conveyer is set to below portal frame, the conveyer is equipped with encoder, on portal frame or conveyer stocks up side equipped with detection sensor device, camera and laser source, the detection sensor device signal connects central processing unit, the central processing unit signal connects the camera and laser source, the camera signal connects image processing module, described image processing module signal connects the central processing unit；The central processing unit is also connected with identification judgment module, and the identification judgment module is connected to Material Sorting equipment.The present apparatus improves to the measurement of contour of object and using computer deep learning algorithm the accuracy rate differentiated to the detection of body form specification using the realization of modern computer vision technique, database is not needed, it can be used as independent device and directly apply to logistic production line, the real-time application with height.
Description
Technical field
The present invention relates to image procossing and machine deep learning technology field, specially a kind of non-regular shape material image
Measure measuring and controlling device and method.
Background technique
At present in logistic industry, especially in baggage sorting system, there has been no detect to body form and judge qualification
Solution, to body form, whether He Ge judgement is completed by people completely.With high costs, accuracy rate varies with each individual completely, very
To different because of the body & mind state of same people, by the way that object picture is carried out pair with there are all samples in its database
Than and judge, real-time application is poor, currently contour of object measurement application technology be using Infrared laser emission and to return
The time returned determines space length of the body surface away from light emitting source, to realize the measurement to contour of object.Since it shines
Source is successively scanned transmitting in a stepwise manner and is received along 180 degree, and speed of detection and precision are straight by stepping rate and amplitude
Connect limitation.For this purpose, it is proposed that a kind of non-regular shape material image measurement measuring and controlling device and method.
Summary of the invention
The purpose of the present invention is to provide a kind of non-regular shape material image measurement measuring and controlling device and methods, on solving
State the problem of proposing in background technique.
To achieve the above object, the invention provides the following technical scheme:
A kind of non-regular shape material image measurement measuring and controlling device, including conveyer and portal frame, conveyer are set to gantry
Below frame, the conveyer is equipped with encoder, and on portal frame or conveyer stocks up side equipped with detection sensor device, camera and laser
Source, the detection sensor device signal connect central processing unit, and the central processing unit signal connects the camera and laser source, institute
Camera signal connection image processing module is stated, described image processing module signal connects the central processing unit；The centre
Reason device is also connected with identification judgment module, and the identification judgment module is connected to Material Sorting equipment；
The encoder is mounted on conveyer power electric arbor or on a conveyor by friction pulley and belt conveyor
Contact.
The detection sensor device is arranged along conveyer traffic direction in portal frame front end.
The camera is equipped with four, is respectively arranged on the left and right sides and upper left and the upper right of portal frame, and shooting direction pair
Quasi- laser source direction of illumination.
There are three the laser source is set, it is respectively arranged on the left and right sides and top of portal frame, direction of illumination alignment conveying
The machine and light irradiated is in the same plane.
Using above-mentioned apparatus to the method for non-regular shape material image measurement prosecution:
S1: using the calibration algorithm of computer vision, establishing every camera can be seen that the sky at visual field midpoint in laser plane
Between in position and its image location of pixels corresponding relationship；
S2: when material enters detection sensor induction range from conveyer forward position, detection sensor sense after by signal
It is sent to central processing unit, laser and camera are opened in central processing unit control, control camera with fixed pulse spacing to material
It carries out slice type to take pictures, until detection sensor senses that material tail end passes through laser projection plane；
S3: image processing module extracts the Points And lines for having laser irradiation feature in camera acquired image,
And by algorithm filter out body surface it is reflective etc. caused by have the interference information of laser feature, identify that real laser is special
Sign, extracts the profile dot matrix of material, and composition is used for the point cloud of three-dimensional modeling；
S4: central processing unit calculated according to the information that image processing module extracts material sectional area, overlook area,
Actual volume, minimum containing volume (i.e. length, width and height maximum value product) are transferred to identification judgment module, the identification judgement
Module is compared according to its corresponding preset data of these data, is identified with this and is judged whether material shapes conform to
It asks, and indicates that material sorting device makes corresponding actions according to judging result.
When some o'clock in laser plane by two or more camera looks into fee then, using binocular vision algorithm to them
It is matched, and optimizes screening away from camera distance according to them.
Compared with prior art, the beneficial effects of the present invention are: the device uses computer vision technique, compared to traditional
Infrared laser scanning technique, its advantage are the relationships that the information being imaged every time is " face " vs " point ", and efficiency greatly improves, and are used
Computer deep learning algorithm improves the accuracy rate differentiated to the detection of body form specification, using computer vision and studies in depth
Whether technology replaces manually, detected to contour of object and volume and judge the object in accordance with application requirement.It does not need to utilize
So-called big data, i.e., by by object picture with there are being judged and all samples in its database compare, but
The data judgment models established using sample analysis carry out qualified judgement to the data of measurement.Database is not needed, can be used as solely
Vertical device directly applies to logistic production line, the real-time application with height.
Detailed description of the invention
Fig. 1 is the mounting structure schematic diagram of the part of module of apparatus of the present invention, and arrow show conveyer traffic direction.
Fig. 2 is invention's principle block diagram.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Non-regular shape material image measurement measuring and controlling device of the invention referring to FIG. 1-2, including conveyer 100 and dragon
Door frame 200, conveyer are set to below portal frame, and conveyer is equipped with encoder (not shown), are mounted on conveying mechanomotive force
It is contacted on motor shaft or on a conveyor by friction pulley with belt conveyor, on portal frame or conveyer stocks up side equipped with detection
Inductor 3, camera 1 and laser source 2, detection sensor device signal connect central processing unit 0, central processing unit signal connect camera and
Laser source, camera signal connect image processing module 4, and image processing module signal connects central processing unit；Central processing unit is also
It is connected with identification judgment module 5, identification judgment module is connected to Material Sorting equipment 6.
The detection sensor device is arranged along conveyer traffic direction in portal frame front end.
Camera is equipped with four, is respectively arranged on the left and right sides and upper left and the upper right of portal frame, and shooting direction alignment swashs
Light source direction of illumination.
There are three laser source is set, be respectively arranged on the left and right sides and top of portal frame, direction of illumination be aligned conveyer and
The light irradiated is in the same plane.
Encoder combination detection sensor determines the accurate location of object on a conveyor, and pulse is supplied to controller use
In the triggering of control camera and switch laser.The numerical value of encoder, the numerical value base are recorded when object forward position enters detection sensor
Value added on plinth is exactly that the advanced position of object opens laser before its forward position enters laser in advance, when advanced position enters
When in laser plane, central processing unit control camera starts triggering and takes pictures, and is taken pictures with fixed intervals triggering；After object along into
When entering detection sensor, record records the numerical value of encoder, and the value added on the basis of the numerical value is exactly the back edge position of object, when
After back edge position enters laser, stops camera triggering and take pictures and close laser, control flash lamp bat takes a recording photograph.
Using above-mentioned apparatus to the method for non-regular shape material image measurement prosecution:
S1: using the calibration algorithm of computer vision, establishing every camera can be seen that the sky at visual field midpoint in laser plane
Between in position and its image location of pixels corresponding relationship；
S2: when material enters detection sensor induction range from conveyer forward position, detection sensor sense after by signal
It is sent to central processing unit, laser and camera are opened in central processing unit control, control camera with fixed pulse spacing to material
It carries out slice type to take pictures, until detection sensor senses that material tail end passes through laser projection plane；
S3: image processing module extracts the Points And lines for having laser irradiation feature in camera acquired image,
And by algorithm filter out body surface it is reflective etc. caused by have the interference information of laser feature, identify that real laser is special
Sign, extracts the profile dot matrix of material, and composition is used for the point cloud of three-dimensional modeling；
S4: central processing unit calculated according to the information that image processing module extracts material sectional area, overlook area,
Actual volume, minimum containing volume (i.e. length, width and height maximum value product) are transferred to identification judgment module, the identification judgement
Module is compared according to its corresponding preset data of these data, is identified with this and is judged whether material shapes conform to
It asks, and indicates that material sorting device makes corresponding actions according to judging result.
When some o'clock in laser plane by two or more camera looks into fee then, using binocular vision algorithm to them
It is matched, and optimizes screening away from camera distance according to them.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (7)
1. a kind of non-regular shape material image measurement measuring and controlling device, which is characterized in that including conveyer and portal frame, conveyer
Below the portal frame, the conveyer is equipped with encoder, and on portal frame or conveyer stocks up side equipped with detection sensor device, phase
Machine and laser source, the detection sensor device signal connect central processing unit, the central processing unit signal connect the camera and
Laser source, the camera signal connect image processing module, and described image processing module signal connects the central processing unit；Institute
It states central processing unit and is also connected with identification judgment module, the identification judgment module is connected to Material Sorting equipment.
2. non-regular shape material image measurement measuring and controlling device according to claim 1, which is characterized in that the encoder
It is mounted on conveyer power electric arbor or is contacted on a conveyor by friction pulley with belt conveyor.
3. non-regular shape material image measurement measuring and controlling device according to claim 1, which is characterized in that the detection sense
Device is answered to be arranged along conveyer traffic direction in portal frame front end.
4. non-regular shape material image measurement measuring and controlling device according to claim 1, which is characterized in that the camera is set
There are four, is respectively arranged on the left and right sides and upper left and the upper right of portal frame, and shooting direction is directed at laser source direction of illumination.
5. non-regular shape material image measurement measuring and controlling device according to claim 1, which is characterized in that the laser source
There are three if, it is respectively arranged on the left and right sides and top of portal frame, the light position that direction of illumination is directed at conveyer and irradiates
In in same plane.
6. a kind of method of non-regular shape material image measurement prosecution, which comprises the following steps:
S1: using the calibration algorithm of computer vision, establishing every camera can be seen that the space bit at visual field midpoint in laser plane
Set the corresponding relationship with location of pixels in its image；
S2: when material enters detection sensor induction range from conveyer forward position, detection sensor sends signal after sensing
To central processing unit, laser and camera are opened in central processing unit control, are controlled camera and are carried out with fixed pulse spacing to material
Slice type is taken pictures, until detection sensor senses that material tail end passes through laser projection plane；
S3: image processing module extracts the Points And lines for having laser irradiation feature in camera acquired image, and leads to
It crosses algorithm and filters out the interference information for having laser feature caused by the reflective grade of body surface, identify real laser feature,
The profile dot matrix of material is extracted, composition is used for the point cloud of three-dimensional modeling；
S4: central processing unit calculates the sectional area of material according to the information that image processing module extracts, overlooks area, reality
Volume, minimum containing volume, are transferred to identification judgment module, the identification judgment module is corresponding to its according to these data
Preset data be compared, identified with this and judge whether material shapes meet the requirements, and according to judging result indicate material
Sorting device makes corresponding actions.
7. the method for non-regular shape material image measurement prosecution according to claim 6, which is characterized in that when laser is flat
Some o'clock in face then, match them using binocular vision algorithm by two or more camera looks into fee, and according to
They optimize screening away from camera distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811556787.4A CN109590231A (en) | 2018-12-19 | 2018-12-19 | A kind of non-regular shape material image measurement measuring and controlling device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811556787.4A CN109590231A (en) | 2018-12-19 | 2018-12-19 | A kind of non-regular shape material image measurement measuring and controlling device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109590231A true CN109590231A (en) | 2019-04-09 |
Family
ID=65964031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811556787.4A Withdrawn CN109590231A (en) | 2018-12-19 | 2018-12-19 | A kind of non-regular shape material image measurement measuring and controlling device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109590231A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110174065A (en) * | 2019-06-17 | 2019-08-27 | 湖南农业大学 | Fruit size lossless detection method based on orthogonal binocular machine vision |
| CN110321836A (en) * | 2019-07-01 | 2019-10-11 | 芜湖启迪睿视信息技术有限公司 | A kind of conveying material detection method based on image and laser point cloud atlas |
| CN110479615A (en) * | 2019-07-18 | 2019-11-22 | 深圳优地科技有限公司 | Express delivery method for sorting, device and terminal device based on unmanned plane |
| CN110653166A (en) * | 2019-10-08 | 2020-01-07 | 河南科技大学 | Fruit detection and classification method and device |
| CN113277341A (en) * | 2021-05-11 | 2021-08-20 | 齐品(杭州)网络科技有限公司 | Packing optimization device based on real contour and volume of object |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090139911A1 (en) * | 2007-11-30 | 2009-06-04 | Nova Chemicals Inc. | Method of detecting defective containers |
| CN104183010A (en) * | 2013-05-22 | 2014-12-03 | 上海迪谱工业检测技术有限公司 | Multi-view three-dimensional online reconstruction method |
| CN206563560U (en) * | 2017-02-17 | 2017-10-17 | 华南理工大学 | A kind of phone housing quality on-line detecting device based on line laser structured light |
| CN107505285A (en) * | 2017-07-26 | 2017-12-22 | 合肥泰禾光电科技股份有限公司 | A kind of online sorting unit of material and its scanning imagery spectral device |
| CN107505324A (en) * | 2017-08-10 | 2017-12-22 | 王兴 | 3D scanning means and scan method based on binocular collaboration laser |
| CN107578464A (en) * | 2017-06-30 | 2018-01-12 | 长沙湘计海盾科技有限公司 | A kind of conveyor belt workpieces measuring three-dimensional profile method based on line laser structured light |
| CN107632022A (en) * | 2017-08-30 | 2018-01-26 | 武汉理工大学 | A kind of detection method of surface flaw of steel rail and device based on data processing |
-
2018
- 2018-12-19 CN CN201811556787.4A patent/CN109590231A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090139911A1 (en) * | 2007-11-30 | 2009-06-04 | Nova Chemicals Inc. | Method of detecting defective containers |
| CN104183010A (en) * | 2013-05-22 | 2014-12-03 | 上海迪谱工业检测技术有限公司 | Multi-view three-dimensional online reconstruction method |
| CN206563560U (en) * | 2017-02-17 | 2017-10-17 | 华南理工大学 | A kind of phone housing quality on-line detecting device based on line laser structured light |
| CN107578464A (en) * | 2017-06-30 | 2018-01-12 | 长沙湘计海盾科技有限公司 | A kind of conveyor belt workpieces measuring three-dimensional profile method based on line laser structured light |
| CN107505285A (en) * | 2017-07-26 | 2017-12-22 | 合肥泰禾光电科技股份有限公司 | A kind of online sorting unit of material and its scanning imagery spectral device |
| CN107505324A (en) * | 2017-08-10 | 2017-12-22 | 王兴 | 3D scanning means and scan method based on binocular collaboration laser |
| CN107632022A (en) * | 2017-08-30 | 2018-01-26 | 武汉理工大学 | A kind of detection method of surface flaw of steel rail and device based on data processing |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110174065A (en) * | 2019-06-17 | 2019-08-27 | 湖南农业大学 | Fruit size lossless detection method based on orthogonal binocular machine vision |
| CN110321836A (en) * | 2019-07-01 | 2019-10-11 | 芜湖启迪睿视信息技术有限公司 | A kind of conveying material detection method based on image and laser point cloud atlas |
| CN110321836B (en) * | 2019-07-01 | 2023-07-21 | 芜湖启迪睿视信息技术有限公司 | Conveyed material detection method based on image and laser point cloud image |
| CN110479615A (en) * | 2019-07-18 | 2019-11-22 | 深圳优地科技有限公司 | Express delivery method for sorting, device and terminal device based on unmanned plane |
| CN110653166A (en) * | 2019-10-08 | 2020-01-07 | 河南科技大学 | Fruit detection and classification method and device |
| CN110653166B (en) * | 2019-10-08 | 2021-10-22 | 河南科技大学 | Fruit detection and classification method and device |
| CN113277341A (en) * | 2021-05-11 | 2021-08-20 | 齐品(杭州)网络科技有限公司 | Packing optimization device based on real contour and volume of object |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109590231A (en) | A kind of non-regular shape material image measurement measuring and controlling device and method | |
| CN104101608B (en) | Intelligent detecting device for detecting defects of multi-type irregularly shaped product | |
| CN102818538B (en) | Detection system based on modulated glass thread structure laser image | |
| CN104764750B (en) | Elevator balanced compensated chain automatic detection device for quality and method based on machine vision | |
| CA2151344C (en) | Lens inspection system and method | |
| CN104198157B (en) | Automatic sorting device with lens detection function | |
| CN110146516B (en) | Fruit grading device based on orthogonal binocular machine vision | |
| CN104729426B (en) | Angle steel automatic on-line detecting system and method based on machine vision | |
| CN201218723Y (en) | Optoelectronic non-contact type image detection apparatus | |
| CN209901748U (en) | Plastic part automatic detection equipment based on machine vision recognition | |
| CN206057205U (en) | A kind of notebook computer assembly quality automatic detection device | |
| CN105865570A (en) | Machine vision-based glass bottle liquid level detection method | |
| CN205861568U (en) | A kind of hexahedro vision inspection apparatus | |
| JP6191204B2 (en) | Appearance inspection apparatus and appearance inspection method for automobile body | |
| CN206981462U (en) | Stamping parts surface defect detection apparatus based on 3D vision | |
| CN211070921U (en) | Instrument appearance detection device based on 3D scanning method | |
| CN108844966A (en) | A kind of screen detection method and detection system | |
| CN106052793A (en) | Machine vision based liquid level sub-quality product marking method | |
| CN106706656A (en) | Machine vision-based zipper detection device and method | |
| CN104123779A (en) | Coin concealed pattern detecting method and detecting device thereof | |
| CN101156060A (en) | Method and device for eliminating parasite reflections during inspection of translucent or transparent hollow objects | |
| CN108387177A (en) | A kind of wheel hub classification detection device and detection method | |
| CN206540843U (en) | A kind of mobile phone shell automatic checkout equipment | |
| CN106353336A (en) | Lens coating automatic detection system | |
| CN105160754A (en) | Coin surface quality detection apparatus and coin surface quality detection method based on height measurement |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190409 |
|
| WW01 | Invention patent application withdrawn after publication |