CN106331620B - Filling production lines medicine bottle method for positioning analyzing - Google Patents

Filling production lines medicine bottle method for positioning analyzing Download PDF

Info

Publication number
CN106331620B
CN106331620B CN201610720592.3A CN201610720592A CN106331620B CN 106331620 B CN106331620 B CN 106331620B CN 201610720592 A CN201610720592 A CN 201610720592A CN 106331620 B CN106331620 B CN 106331620B
Authority
CN
China
Prior art keywords
video camera
target
medicine bottle
image
imaging face
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
Application number
CN201610720592.3A
Other languages
Chinese (zh)
Other versions
CN106331620A (en
Inventor
于玥
韩天顺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Otsuka Pharmaceutical Co Ltd
Original Assignee
China Otsuka Pharmaceutical Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Otsuka Pharmaceutical Co Ltd filed Critical China Otsuka Pharmaceutical Co Ltd
Priority to CN201610720592.3A priority Critical patent/CN106331620B/en
Publication of CN106331620A publication Critical patent/CN106331620A/en
Application granted granted Critical
Publication of CN106331620B publication Critical patent/CN106331620B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/18Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/183Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30241Trajectory

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Image Analysis (AREA)
  • Medical Preparation Storing Or Oral Administration Devices (AREA)

Abstract

The invention discloses a kind of filling production lines medicine bottle method for positioning analyzing, rely on image processing module, transmission system and controller, and the hardware platform of the video camera composition in transmission system is set, the image data stream of video camera output, successively by the image acquisition units inside described image processing module, digitized processing unit, feature extraction unit tests and analyzes unit;The transmission speed of the distance between medicine bottle and video camera and medicine bottle on a moving belt is calculated finally by calculation formula, further medicine bottle is positioned.Rapidly, accuracy is high for present invention positioning, does not need manually to participate in substantially after algorithm setting, saves cost.

Description

Filling production lines medicine bottle method for positioning analyzing
Technical field
The present invention relates to a kind of electricity detecting system fields, more particularly, to a kind of medicine for drug filling production lines Bottle method for positioning analyzing.
Background technique
The liquid drug of pharmaceutical factory's production, is transmitted on assembly line mainly by conveyer belt, in actual production process, certain Production link, such as defective products detection and rejecting stage, need several worker's manual inspections;This intricate operation is uninteresting, Gong Renrong It is easily tired out and slack, seriously affect inspection quality;In addition, heavy workload, for enterprise, the cost of labor of investment is not also low.
To solve the above problems, mechanical clamp, which can be used, replaces artificial clamping medicine bottle.But it for different production lines, passes The transfer rate of band is sent, the interval of adjacent medicine bottle on conveyer belt, the size shape etc. of medicine bottle is all different;Common machinery Fixture is difficult to adaptively again.It is then desired to which designing a kind of can help mechanical clamp to adapt to different production processes automatically Device.Meanwhile in order to guarantee clamping process rapidly and accurately, it is necessary first to the position for medicine bottle of having good positioning;And medicine bottle moment itself It is moved on assembly line, thus also needs to judge the movement velocity and motion profile of medicine bottle;Thus need to design a kind of medicine bottle Method for positioning analyzing.
Summary of the invention
The present invention is intended to provide a kind of filling production lines medicine bottle method for positioning analyzing, to improve the above problem.In order to realize Above-mentioned purpose, the present invention provides a kind of filling production lines medicine bottle method for positioning analyzing, this method is relied on by video camera, image The hardware system of the equipment such as processing module, transmission system and controller composition, the video camera setting is in conveyer belt side, camera shooting Machine camera lens primary optical axis is mutually perpendicular to conveyer belt direction of transfer;The first target and the second target are additionally provided in system, two targets are equal For rectangle, size is identical;First target and the line of the second Target Center position are mutually perpendicular to conveyer belt direction of transfer;The One target and the second target and conveyer belt center line are equidistant;Image processing module is connected by video line with video camera;Video camera The image data stream of output, successively by the image acquisition units inside described image processing module, digitized processing unit is special Extraction unit is levied, unit is tested and analyzed;The output end for testing and analyzing unit connects controller;The controller passes through control Bus connects transmission system.
The video camera is by the transmission of video photographed to image processing module;Image data is acquired in frames in image acquisition units And it is sent to buffer area;Digitized processing unit carries out colour space transformation to the picture frame of caching, becomes YUV422 format Digital picture;Feature extraction unit extracts the indicatrix of target object from transformed digital picture, finds feature song The corresponding pixel collection of line, and determine coordinate position of all pixels in entire image;It is logical to test and analyze unit The corresponding pixel variation of indicatrix in multiframe consecutive image is crossed, the real time position and movement velocity of target object are calculated, And anticipation is made to the motion profile of target object;The distance between medicine bottle and video camera D, the transmission speed of medicine bottle on a moving belt V is spent, by equation group
It determines;Wherein,
Horizontal distance between s: two targets;
D: the distance between two neighboring pixel in video camera imaging face;
Number of a: the first target long side in the corresponding horizontal pixel point in video camera imaging face;
Number of b: the first target long side in the corresponding longitudinal pixel in video camera imaging face;
Number of m: the second target long side in the corresponding horizontal pixel point in video camera imaging face;
Number of n: the second target long side in the corresponding longitudinal pixel in video camera imaging face;
The length on the side q: target AB;
G: the frame per second of video camera shooting image;
The frame number being spaced between h: two sub-sampling frames;
Pi: target object ith feature point motion track is in the corresponding horizontal pixel point number in video camera imaging face;
Qi: target object ith feature point motion track is in the corresponding longitudinal pixel number in video camera imaging face;
X: target object feature point number.
The video camera is not less than the image of 720P resolution ratio with the speed shooting of no less than 30 frames per second.
The eyeglass that the video camera uses is aspheric optical lens.
The invention has the advantages that video camera can obtain the present invention by 30 frame per second or higher sample rate in real time Can scene on the conveyer belt in opereating specification, and Image Real-time Transmission is given to the image analysis mould being located in the first control box Block, image analysis module are further processed image, according to characteristic point analysis, find target medicine bottle, and analyze and work as forward pass Send the speed of service of band.Rapidly, accuracy is high for present invention positioning, does not need manually to participate in substantially after algorithm setting, saves cost.
Detailed description of the invention
Fig. 1 is the system structure diagram of invention;
Fig. 2 is the optical imagery figure of invention.
Wherein:
1. conveyer belt;2. camera lens;
3. the first target;4. the second target;
5. primary optical axis.
Specific embodiment
The present invention is described further with reference to the accompanying drawings and embodiments.
As shown in Figure 1, a kind of filling production lines medicine bottle method for positioning analyzing, this method is relied on by video camera, at image Module is managed, the hardware system of the equipment such as transmission system and controller composition, the video camera setting is in transmission system;It is described to take the photograph Camera is arranged in 1 side of conveyer belt, and 2 primary optical axis 5 of camera lens is mutually perpendicular to 1 direction of transfer of conveyer belt;It is also set in system There are the first target 3 and the second target 4, two targets are rectangle, and size is identical;4 center of first target 3 and the second target Line be mutually perpendicular to 1 direction of transfer of conveyer belt;First target 3 and the second target 4 and 1 center line of conveyer belt are equidistant;Image Processing module is connected by video line with video camera;The image data stream of video camera output, successively handles mould by described image Image acquisition units inside block, digitized processing unit, feature extraction unit test and analyze unit;The detection and analysis are single The output end of member connects controller;The controller connects transmission system by control bus.
Video camera is not less than the image of 720P resolution ratio with the speed shooting of no less than 30 frames per second.
Video camera is by the transmission of video photographed to image processing module;Image acquisition units in image processing module press frame It obtains image data and is sent to buffer area;Digitized processing unit carries out colour space transformation to the picture frame of caching, becomes At the digital picture of YUV422 format;The feature that feature extraction unit extracts target object from transformed digital picture is bent Line finds the corresponding pixel collection of indicatrix, and determines coordinate position of all pixels in entire image;Inspection Analytical unit is surveyed by the corresponding pixel variation of indicatrix in multiframe consecutive image, calculates the real time position of target object And movement velocity, and anticipation is made to the motion profile of target object;As shown in Fig. 2, between medicine bottle and camera lens away from From D, the transmission speed V of medicine bottle on a moving belt, by equation group
It determines;Wherein,
Horizontal distance between s: two targets;
D: the distance between two neighboring pixel in video camera imaging face;
Number of a: the first target long side in the corresponding horizontal pixel point in video camera imaging face;
Number of b: the first target long side in the corresponding longitudinal pixel in video camera imaging face;
Number of m: the second target long side in the corresponding horizontal pixel point in video camera imaging face;
Number of n: the second target long side in the corresponding longitudinal pixel in video camera imaging face;
The length on the side q: target AB;
G: the frame per second of video camera shooting image;
The frame number being spaced between h: two sub-sampling frames;
Pi: target object ith feature point motion track is in the corresponding horizontal pixel point number in video camera imaging face;
Qi: target object ith feature point motion track is in the corresponding longitudinal pixel number in video camera imaging face;
X: target object feature point number.
The eyeglass that the video camera uses is aspheric optical lens.
The specific position of assembly line is arranged in the present invention, considers the moving range of transmission system, needs to guarantee no matter be driven How system moves, the conveyer belt scene that the video camera being mounted in transmission system takes all be clearly, and target begin Eventually in scene.Thus video camera selects the model of the big depth of field;It installs and video camera is connected on display first, turn Camera lens focus clear.
Transmission system, as power, is controlled video camera and fixture all around acts by servo motor.
When the invention works, video camera is directed at conveyer belt shooting always, and 30 frame per second or more, every frame image is mentioned through feature After taking, the edge for analyzing and determining out scene Chinese medicine bottle can be transferred through, medicine bottle edge is mapped to the corresponding picture of the profile in imaging surface Vegetarian refreshments coordinate can equally obtain the corresponding pixel coordinate on imaging surface of medicine bottle edge newly it is found that after x frame;Equally, The corresponding pixel coordinate in the edge of target and situation of change are also known;Above-mentioned numerical value is brought into equation group (1) Obtain the distance of current camera distance of camera lens medicine bottle;Due to the capture rate per second for being not less than 30 frames, and this calculating process pair For processor, 1/30 second time is enough;Thus the motion conditions of medicine bottle can be monitored in real time in this system, that is, realize medicine The real-time accurate positioning of bottle.

Claims (3)

1. a kind of filling production lines medicine bottle method for positioning analyzing, it is characterised in that: this method relies on hardware system, the hardware System includes video camera, image processing module, transmission system and controller;The video camera setting is taken the photograph in conveyer belt (1) side Camera lens (2) primary optical axis (5) is mutually perpendicular to conveyer belt (1) direction of transfer;The first target (3) and second are additionally provided in system Target (4), two targets are rectangle, and size is identical;The line and biography of first target (3) and the second target (4) center Band direction of transfer is sent to be mutually perpendicular to;First target (3) and the second target (4) and conveyer belt (1) center line are equidistant;Image procossing mould Block is connected by video line with video camera;The image data stream of video camera output, successively by inside described image processing module Image acquisition units, digitized processing unit, feature extraction unit, test and analyze unit;It is described to test and analyze the defeated of unit Outlet connects controller;The controller connects transmission system by control bus;
The video camera is by the transmission of video photographed to image processing module;Image acquisition units are acquired in frames image data and will It is sent into buffer area;Digitized processing unit carries out colour space transformation to the picture frame of caching, becomes the number of YUV422 format Word image;Feature extraction unit extracts the indicatrix of target object from transformed digital picture, finds indicatrix pair The pixel collection answered, and determine coordinate position of all pixels in entire image;Detection and analysis unit passes through more The corresponding pixel variation of indicatrix, calculates the real time position and movement velocity of target object, and right in frame consecutive image The motion profile of target object makes anticipation;The distance between medicine bottle and video camera D, the transmission speed V of medicine bottle on a moving belt, By equation group
It determines;Wherein,
Horizontal distance between s: two targets;
D: the distance between two neighboring pixel in video camera imaging face;
Number of a: the first target long side in the corresponding horizontal pixel point in video camera imaging face;
Number of b: the first target long side in the corresponding longitudinal pixel in video camera imaging face;
Number of m: the second target long side in the corresponding horizontal pixel point in video camera imaging face;
Number of n: the second target long side in the corresponding longitudinal pixel in video camera imaging face;
The length on the side q: target AB;
G: the frame per second of video camera shooting image;
The frame number being spaced between h: two sub-sampling frames;
Pi: target object ith feature point motion track is in the corresponding horizontal pixel point number in video camera imaging face;
Qi: target object ith feature point motion track is in the corresponding longitudinal pixel number in video camera imaging face;
X: target object feature point number.
2. a kind of filling production lines medicine bottle method for positioning analyzing according to claim 1, which is characterized in that the video camera It is not less than the image of 720P resolution ratio with the speed shooting of no less than 30 frames per second.
3. a kind of filling production lines medicine bottle method for positioning analyzing according to claim 2, which is characterized in that the video camera The eyeglass used is aspheric optical lens.
CN201610720592.3A 2016-08-25 2016-08-25 Filling production lines medicine bottle method for positioning analyzing Active CN106331620B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610720592.3A CN106331620B (en) 2016-08-25 2016-08-25 Filling production lines medicine bottle method for positioning analyzing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610720592.3A CN106331620B (en) 2016-08-25 2016-08-25 Filling production lines medicine bottle method for positioning analyzing

Publications (2)

Publication Number Publication Date
CN106331620A CN106331620A (en) 2017-01-11
CN106331620B true CN106331620B (en) 2019-03-29

Family

ID=57790758

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610720592.3A Active CN106331620B (en) 2016-08-25 2016-08-25 Filling production lines medicine bottle method for positioning analyzing

Country Status (1)

Country Link
CN (1) CN106331620B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000263475A (en) * 1999-03-18 2000-09-26 Seiko Seiki Co Ltd Marking device by tracking conveyance
CN103895042A (en) * 2014-02-28 2014-07-02 华南理工大学 Industrial robot workpiece positioning grabbing method and system based on visual guidance
CN104108579A (en) * 2014-07-15 2014-10-22 上海发那科机器人有限公司 Device and method for positioning workpiece on linear conveyor belt through visual system
CN104217441A (en) * 2013-08-28 2014-12-17 北京嘉恒中自图像技术有限公司 Mechanical arm positioning fetching method based on machine vision
CN104786226A (en) * 2015-03-26 2015-07-22 华南理工大学 Posture and moving track positioning system and method of robot grabbing online workpiece

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000263475A (en) * 1999-03-18 2000-09-26 Seiko Seiki Co Ltd Marking device by tracking conveyance
CN104217441A (en) * 2013-08-28 2014-12-17 北京嘉恒中自图像技术有限公司 Mechanical arm positioning fetching method based on machine vision
CN103895042A (en) * 2014-02-28 2014-07-02 华南理工大学 Industrial robot workpiece positioning grabbing method and system based on visual guidance
CN104108579A (en) * 2014-07-15 2014-10-22 上海发那科机器人有限公司 Device and method for positioning workpiece on linear conveyor belt through visual system
CN104786226A (en) * 2015-03-26 2015-07-22 华南理工大学 Posture and moving track positioning system and method of robot grabbing online workpiece

Also Published As

Publication number Publication date
CN106331620A (en) 2017-01-11

Similar Documents

Publication Publication Date Title
CN109862345B (en) Method and system for testing field angle
CN102589516A (en) Dynamic distance measuring system based on binocular line scan cameras
CN102879404B (en) System for automatically detecting medical capsule defects in industrial structure scene
CN106053473A (en) Device and method utilizing mechanical arm to carry out visual positioning detection
CN115760893A (en) Single droplet particle size and speed measuring method based on nuclear correlation filtering algorithm
CN109631763A (en) Irregular part detects localization method
CN106331620B (en) Filling production lines medicine bottle method for positioning analyzing
CN206023988U (en) A kind of filling production lines medicine bottle positioning analysises system
CN106162102B (en) Filling production line medicine bottle positioning analysis system
CN108416763B (en) Image edge processing method for relay measurement
CN111475016A (en) Assembly process geometric parameter self-adaptive measurement system and method based on computer vision
CN206583440U (en) A kind of projected image sighting distance detecting system
CN207730156U (en) A kind of automobile tube beam measuring device
CN110675393A (en) Blank specification detection method based on machine vision
CN105115434A (en) In-situ measuring device of spacing and depth of V-shaped grooves of conductive rods
CN106770334B (en) A kind of automatic detection platform and its detection method for tempered glass
CN109822478A (en) A kind of comprehensive detection system and method for automobile axial workpiece
CN205861144U (en) The gas meter counter direct readout of digital image understanding technology
CN108427949B (en) Image processing and image expansion method for relay measurement
US20070065042A1 (en) Method for measuring dimensions by means of a digital camera
CN108416762B (en) Image extraction and image processing method for relay measurement
CN204462038U (en) A kind of electric connector housing machine vision on-line detecting system
CN111330869A (en) Visual detection method and system for on-line grading of lens
CN110823139A (en) Measuring method of multi-angle reflector
CN1796987A (en) Optical detection device and detection method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant