CN2923067Y - Multi-path fruit vision grading picture collector - Google Patents
Multi-path fruit vision grading picture collector Download PDFInfo
- Publication number
- CN2923067Y CN2923067Y CN 200620117747 CN200620117747U CN2923067Y CN 2923067 Y CN2923067 Y CN 2923067Y CN 200620117747 CN200620117747 CN 200620117747 CN 200620117747 U CN200620117747 U CN 200620117747U CN 2923067 Y CN2923067 Y CN 2923067Y
- Authority
- CN
- China
- Prior art keywords
- fruit
- transfer structure
- video camera
- image collecting
- collecting device
- 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
Images
Landscapes
- Sorting Of Articles (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model relates to a graphic data collection device, particularly the fruit surface graphic data collection device used for the automatic fruit vision grading. The utility model provides a multi channel fruit vision grading graphic data collection device which comprises a computer and a data collection card. The utility model includes also a conveyor structure to move the fruit, a video camera above the conveyor structure to capture the fruit surface graphic data, a switch to control the movement of the video camera. The conveyor structure has multi channels and the video camera can capture the images of fruit on multiple conveyor channels. The utility model is characterized in that the utility model has low information redundancy, quick grading, and high grading efficiency. Only one video camera is needed to handle multiple channel data. The data collection device has a simple structure and is easy to be realized.
Description
Technical field
The utility model relates to a kind of image data acquiring device, particularly a kind of fruit surface image collecting device that is used for the automatic classification of fruit vision.This technology belongs to modern agriculture equipment field.
Background technology
China is fruit big producing country, and the fruit resource is very abundant, and output occupies first of the world, but export volume only accounts for very little ratio.One of them reason that causes this contrast is that detection behind the fruit picking, classification technique fall behind.Present domestic most of fruit is just handled directly listing without commercialization after harvesting, fruit finished product grade mixes, and is very different, influenced the commodity value of fruit, and commodity are lacked competitiveness in the international market, seriously cut down its international market share.
The key link that commercialization behind the fruit picking is handled comprise select, clean, waxing, classification and packing etc., wherein classification is the core link during commercialization is handled.At present, the fruit grading of China is handled main still dependence and is manually finished, and the labour that such processing method needs is many, labour intensity is big, and the result of classification can be bigger because of labourer's individual difference difference, and the uniformity of grading effect is relatively poor, and efficient is also lower.Some mechanization classifying equipoments that come into operation mainly are to rely on size, size, the weight of fruit to carry out classification both at home and abroad, and the standard of classification is more single, is difficult to satisfy the needs in market.Though the technology in this field has its limitation at present, but, utilize machinery operation that fruit is carried out the vision classification and have very big advantage, can be simultaneously to a plurality of standards, comprising that the exterior quality such as size, shape, color, blemish of fruit is disposable carries out comprehensive classification.The objectivity of classification is strong, standard is stable, high conformity, efficient height, and noncontact do not have injury, thereby has good application prospects.
Utilizing machine vision to carry out in the classification of fruit, the whether accurate final classification results and the classification efficiency of being related to of fruit surface image information collection.It is at the picture rich in detail that guarantees to get access to as much as possible under certain working (machining) efficiency whole fruit surface that fruit image is gathered basic demand.Domestic existing fruit vision hierarchy system substantially all is that single passage is gathered, even there are two or more passages, also mainly be that the form that adopts each passage that a camera, the responsible passage of each camera are installed is carried out IMAQ, the integrated level of system is lower.In addition, mainly contain dual mode on the sequential of IMAQ: a kind of is video camera continuous acquisition and output, with the redundancy of software judgement number of image frames, removes redundant frame, obtains effective information; Another kind is video camera continuous acquisition and output, uses hardware mode simultaneously, promptly adopts the capture card with external trigger pattern to carry out IMAQ, removes redundant picture frame, obtains effective information.But no matter any acquisition mode all incomplete fruit image may occur in a two field picture, has directly influenced the result and the efficient of fruit grading.
The utility model content
(1) technical problem that will solve
The purpose of this utility model is the defective that will overcome present prior art, proposes a kind ofly only to use a video camera, and the multichannel fruit vision grading plant that the information redundancy amount is low, hierarchical speed is fast, classification efficiency is high.
(2) technical scheme
The utility model proposes a kind of multichannel fruit vision classification image collecting device, comprise all-purpose computer and the image data acquiring card that is used to handle the data that collect, also comprise transfer structure, the video camera that is used to catch the fruit surface view data that is positioned at the transfer structure top that is used to transmit fruit, the construction of switch that is used to control the video camera action, wherein transfer structure has a plurality of transmission passages, and the shooting function is caught the fruit image on a plurality of transmission passages simultaneously.
The multichannel fruit vision classification image collecting device that the utility model proposes, a kind of preferred scheme is that construction of switch comprises coding disk and near switch, there is equally distributed notch the outer ring of coding disk.Notch number and transfer structure are complementary.According to moving of transfer structure, a notch will be arranged through surveyed area on the coding disk near switch, make near pulse of switch output.
Above-mentioned multichannel fruit vision classification image collecting device, another kind of preferred scheme is also to comprise level translator, is used to connect video camera and near switch, satisfies video camera and near the electric coupling of switch.
The multichannel fruit vision classification image collecting device that the utility model proposes, a kind of preferred scheme are that transfer structure has two transmission passages.Transfer structure is preferably two groups of chain conveyors, is synchronized with the movement by same chain wheel drive, roller and pallet are installed on the conveyer belt, and roller can be around the horizontal axis rotation of self.
Preferably, be provided with side plate in the conveyer belt both sides, offer chute on the side plate, the shape of chute can be represented by the formula:
R is the distances of guide finger 12 centers to roller centre in the formula, and ω is the rotational angular velocity of roller, and v is the speed of conveyer belt, and t is a run duration.
The multichannel fruit vision classification image collecting device that the utility model proposes, a kind of preferred scheme is also to comprise lighting apparatus, lighting apparatus is installed near the transfer structure as the light source of transfer structure.This lighting apparatus is preferably high-frequency florescent lamp.
(3) beneficial effect
Adopt the utility model,, carry out the graded operation of a plurality of fruit simultaneously, improve operating efficiency on the one hand by multichannel transfer structure.
On the other hand, the utility model only uses a video camera, not only saves cost, and simple in structure, the level of integrated system height.
Since adopt coding disk and, make the utility model can catch the image of fruit different angles near the design of switch, the image data positional precision height of gained, and also the view data amount of redundancy is little, is convenient to follow-up data and handles.
Moreover the utility model supplementary equipment therefore for example scheme of lighting apparatus simply is easy to realize.
Description of drawings
Fig. 1 is the system architecture schematic diagram;
Fig. 2 is the system works schematic diagram, and wherein (a) is front view, (b) is lateral plan;
Fig. 3 is the IMAQ sequential chart, and wherein (a) is the n time triggering, (b) is the n+1 time triggering, (c) is the n+2 time triggering.
Wherein, 1, sprocket wheel; 2, chain conveyor; 3, near switch; 4, coding disk; 5, roller; 6, pallet; 7, fruit; 8, chute; 9, fluorescent tube; 10, lamp box; 11, video camera; 12, guide finger; 13, side plate; 14, transfer structure.
The specific embodiment
The multichannel fruit vision classification image collecting device that the utility model proposes is described as follows in conjunction with the accompanying drawings and embodiments.Following embodiment only is used to illustrate the utility model; and be not to restriction of the present utility model; the those of ordinary skill in relevant technologies field; under the situation that does not break away from spirit and scope of the present utility model; can also make various variations and modification; therefore all technical schemes that are equal to also belong to category of the present utility model, and scope of patent protection of the present utility model should be limited by each claim.
With reference to Fig. 1, multichannel fruit vision classification image collecting device of the present utility model mainly comprises with the lower part: all-purpose computer, be used to handle the data that collect the image data acquiring card, be used to transmit fruit transfer structure 14, be used to catch the fruit surface view data video camera 11, be used to control the coding disk 4 of video camera action and near switch 3, and be used to connect video camera and near the level translator of switch.
Wherein, present embodiment selects for use a colour TV camera of lining by line scan of the supporting asynchronous reset OK_AC1300 of image technique company (in the good perseverance in Beijing from) and Color Image Acquisition card (OK-RGB10 from image technique company is praised in the perseverance in Beijing) as image acquisition equipment.Image pick-up card links to each other with computer by pci bus interface.The analog signal of video camera output obtains digital picture and is input to computer carrying out subsequent treatment through after the acquisition process of image pick-up card.
The function that the above-mentioned video camera of selecting for use has the standard interlacing scan or lines by line scan, in the present embodiment, this video camera operates mainly under the progressive scanning mode of external trigger.For the speed that cooperates fruit to transmit, regularly obtain effective information, reduce data redundancy, therefore designed a coding disk, and be used one and as triggering signal the source take place near switch, the action of control video camera.The pulse signal that produces near switch inputs to the control signal of video camera as triggering collection.For satisfying, add a level translator between the two near the electric coupling between switch and the video camera.Video camera keeps wait state always under the situation that does not have the trigger impulse input, no picture signal output.When the trailing edge of a start pulse signal arrived, video camera was carried out the asynchronous reset action at once and is begun the exposure and the scanning of a two field picture, exports a two field picture, was in wait state again after output is finished.
With reference to Fig. 2, present embodiment is used to illustrate twin-channel situation, and promptly device can obtain the surface image information of two fruit simultaneously.Therefore, in an embodiment, the chain conveyor 2 of two groups of structural similarities is synchronized with the movement by sprocket wheel 1 driving of same axle, constitutes the binary channels transmission system.The conveyer belt equal intervals is equipped with roller 5 and pallet 6, and roller can be around the horizontal axis rotation of self.In the transmission course of fruit, can place a fruit 7 on the pallet between per two adjacent rollers.Video camera 11 is installed in directly over conveyer belt vertical, between two passages, makes that the IMAQ plane can be across two passages.Coding disk 4 is installed on the driven shaft of transmission system, coding disk and near switch 3 cooperatings to produce pulse output.There is uniform notch the outer ring of coding disk, and notch number and the driven shaft roller number that conveyer belt moves that whenever turns around equates.So conveyer belt whenever moves the spacing of a roller, a notch will be arranged through surveyed area on the coding disk near switch, make near pulse of switch output.
Pulse near switch output is carried out the collection of a two field picture through triggering video camera after the conversion of level translator at once.Owing to adopt the asynchronous reset video camera to carry out IMAQ, produce the very short microsecond level that reaches of the time of image between beginning to expose from pulse triggering signal, the distance of conveyer belt can be ignored around here, and conveyer belt adopts chain drive structure, so the position of fruit image in every two field picture is constant substantially, select suitable image acquisition region just can guarantee that each fruit in each image all is complete as long as adjust the position of video camera, this will be very beneficial for subsequent image processing.
In order to collect the whole surface information of fruit, fruit not only advances with conveyer belt and does translation, and rotate under the effect of roller through image acquisition region the time.Its principle that rotatablely moves is: in image acquisition region, offer chute 8 on the side plate 13 of conveyer belt both sides.The shape of chute can be represented by the formula:
R is the distances of guide finger 12 centers to roller centre in the formula, and ω is the rotational angular velocity of roller, and v is the speed of conveyer belt, and t is a run duration.When roller process image acquisition region, the center of roller is along x axle uniform motion, the guide finger that is fixed on the roller enters in the chute, guide finger is subjected to the constraint of chute can only be along the orbiting motion of chute, so the compound motion of roller will be on one side with the conveyer belt translation, around own level axle rotate on one side.Under the effect of frictional force, the rotation of roller drives fruit indirectly and rotates.Select different ω can change the angle that roller is turned over through the entire image pickup area time.Evidence, roller is at the whole surface information that can collect fruit through about 240 degree of rotation in the process of image acquisition region.
When the image of the fruit of taking moving, for fear of because the image that the relative motion between fruit and the video camera causes fuzzy, video camera gatherer process used speed as the electronic shutter of 1/1000s to shorten the time for exposure.Illumination condition becomes extremely important in the case, need use additional illumination for fear of the not enough quality of image that guarantees of image exposure.In the present embodiment, fluorescent tube 9 has been installed in the both sides of lamp box 10.Because fluorescent lamp can produce stroboscopic along with the frequency of alternating current,, be operated in the stroboscopic that can produce 100Hz under the power frequency of 50Hz if adopt common fluorescent tube.Because the 1/1000s time for exposure is more much smaller than the cycle strobe of 1/100s, the mean flow rate of taking each two field picture that obtains has bigger fluctuation, causes the loss of target effective information or has strengthened the subsequent image processing difficulty.In order to solve the influence of flicker from fluorescent lighting, present embodiment has adopted the high-frequency florescent lamp of operating frequency 35KHz as light source.So each time for exposure comprises about 35 cycle strobes, the basic elimination because the brightness of image fluctuation that stroboscopic causes obtains good lighting effect.
As shown in Figure 3, be fruit residing state in continuous three triggering collection image process of wherein first passage above, be the fruit image residing position in whole two field picture that collects corresponding to each time below.When carrying out IMAQ, the spacing of a roller of the every motion of conveyer belt, video camera will receive one from the pulse signal near switch, and the exposure and the scanning of the two field picture that will begin in a minute.As shown in Figure 3, the width of image acquisition region on the direction of motion of conveyer belt is set to the spacing of three rollers, so each passage will have three fruit to be photographed in every two field picture, has the image of six fruit on promptly every two field picture.
On the other hand, because the width of image acquisition region is the distance of three rollers, so each fruit will be collected three times in by the process of whole pickup area, promptly the full detail of whole fruit is distributed in the three frame continuous images.Among Fig. 3, when the n time triggering of video camera, collect A ', the B ' of A, B, C and the passage two of passage one, the image that C ' has six fruit altogether.When triggering for the n+1 time, each fruit of acquisition zone has moved forward the distance of a roller, certain angle of under the effect of roller rotation, overturning simultaneously, wherein fruit A and A ' have shifted out pickup area, corresponding fruit D and the D ' that closelys follow in fruit C and C ' back enters pickup area, the image of fruit B, C and B ', collected another angle of C '.In like manner, when the n+2 triggering, B and B ' shift out pickup area, and E and E ' enter pickup area, and fruit C and C ' are collected image for the third time.According to above-mentioned, after three continuous triggerings, the image of collected three different surfaces of fruit C and C '.
After above-mentioned image carries out relevant treatment through the graph data capture card, cooperate image processing software resulting fruit image is handled and to be judged, obtain to select the information foundation of fruit by all-purpose computer.All-purpose computer and required image processing software are the modern common technology that person skilled is familiar with, and do not give unnecessary details at this.
Adopt multi-path fruit vision grading picture collector of the present utility model to carry out the fruit image collection, and with the acquisition result as the data foundation of fruit grading after this, the contrast prior art, its advantage is very abundant:
(1) device is operated under the multichannel condition simultaneously, has greatly improved the effect of fruit grading Rate;
(2) solve the IMAQ of a plurality of passages with a video camera, simple in structure, system The integrated level height;
(3) design of employing coding disk and approach switch, the image of seizure fruit different angles, The image data positional precision height of gained, and the view data amount of redundancy is little, is convenient to follow-up number According to processing;
(4) the photoenvironment scheme simply is easy to realize;
(5) hardware cost is low, is suitable for batch machining.
Claims (10)
1, a kind of multichannel fruit vision classification image collecting device, comprise all-purpose computer and the image data acquiring card that is used to handle the data that collect, it is characterized in that also comprising transfer structure, the video camera that is used to catch the fruit surface view data that is positioned at the transfer structure top that is used to transmit fruit, the construction of switch that is used to control the video camera action, wherein transfer structure has a plurality of transmission passages, and the shooting function is caught the fruit image on a plurality of transmission passages simultaneously.
2, multichannel fruit vision classification image collecting device as claimed in claim 1 is characterized in that construction of switch comprises coding disk and near switch, there is equally distributed notch the outer ring of coding disk.
3, multichannel fruit vision classification image collecting device as claimed in claim 2 is characterized in that also comprising level translator, is used to connect video camera and near switch, satisfies video camera and near the electric coupling of switch.
4,, it is characterized in that transfer structure has two and transmits passage as claim 1,2 or 3 described multichannel fruit vision classification image collecting devices.
5, multichannel fruit vision classification image collecting device as claimed in claim 4, it is characterized in that transfer structure is two groups of chain conveyors, chain wheel drive by same axle is synchronized with the movement, and roller and pallet are installed on the conveyer belt, and roller can be around the horizontal axis rotation of self.
6, multichannel fruit vision classification image collecting device as claimed in claim 5 is characterized in that being provided with side plate (13) in the conveyer belt both sides, offers chute (8) on the side plate (13), and the shape of chute (8) can be represented by the formula:
R is the distance of guide finger (12) center to roller centre in the formula, and ω is the rotational angular velocity of roller, and v is the speed of conveyer belt, and t is a run duration.
7, as claim 1,2,3 or 6 described multichannel fruit vision classification image collecting devices, it is characterized in that also comprising lighting apparatus, lighting apparatus is installed near the transfer structure as the light source of transfer structure.
8, multichannel fruit vision classification image collecting device as claimed in claim 4 is characterized in that also comprising lighting apparatus, and lighting apparatus is installed near the transfer structure as the light source of transfer structure.
9, multichannel fruit vision classification image collecting device as claimed in claim 5 is characterized in that also comprising lighting apparatus, and lighting apparatus is installed near the transfer structure as the light source of transfer structure.
10, multichannel fruit vision classification image collecting device as claimed in claim 7 is characterized in that lighting apparatus is a high-frequency florescent lamp.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200620117747 CN2923067Y (en) | 2006-06-21 | 2006-06-21 | Multi-path fruit vision grading picture collector |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200620117747 CN2923067Y (en) | 2006-06-21 | 2006-06-21 | Multi-path fruit vision grading picture collector |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN2923067Y true CN2923067Y (en) | 2007-07-18 |
Family
ID=38259490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200620117747 Expired - Fee Related CN2923067Y (en) | 2006-06-21 | 2006-06-21 | Multi-path fruit vision grading picture collector |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN2923067Y (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102274833A (en) * | 2011-04-26 | 2011-12-14 | 浙江大学 | Automatic grading device of botrytis of solanaceous vegetables |
| CN101322969B (en) * | 2008-07-18 | 2012-11-14 | 中国农业大学 | Test and classification method |
| CN103111427A (en) * | 2013-01-10 | 2013-05-22 | 上海交通大学 | Fruit grader based on image processing |
| CN103185609A (en) * | 2011-12-29 | 2013-07-03 | 机械科学研究总院先进制造技术研究中心 | Image detecting method for grading of tomatoes |
| CN104609102A (en) * | 2015-01-13 | 2015-05-13 | 山东农业大学 | Dynamic corn seed image acquisition conveying belt |
| CN105597911A (en) * | 2016-01-07 | 2016-05-25 | 何天柱 | Fruit sorting method |
| CN113177925A (en) * | 2021-05-11 | 2021-07-27 | 昆明理工大学 | Method for nondestructive detection of fruit surface defects |
| CN114160434A (en) * | 2021-12-09 | 2022-03-11 | 中通服供应链管理有限公司江西分公司 | Automatic dynamic sorting and carrying system |
-
2006
- 2006-06-21 CN CN 200620117747 patent/CN2923067Y/en not_active Expired - Fee Related
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101322969B (en) * | 2008-07-18 | 2012-11-14 | 中国农业大学 | Test and classification method |
| CN102274833A (en) * | 2011-04-26 | 2011-12-14 | 浙江大学 | Automatic grading device of botrytis of solanaceous vegetables |
| CN103185609A (en) * | 2011-12-29 | 2013-07-03 | 机械科学研究总院先进制造技术研究中心 | Image detecting method for grading of tomatoes |
| CN103111427A (en) * | 2013-01-10 | 2013-05-22 | 上海交通大学 | Fruit grader based on image processing |
| CN103111427B (en) * | 2013-01-10 | 2014-08-27 | 上海交通大学 | Fruit grader based on image processing |
| CN104609102A (en) * | 2015-01-13 | 2015-05-13 | 山东农业大学 | Dynamic corn seed image acquisition conveying belt |
| CN105597911A (en) * | 2016-01-07 | 2016-05-25 | 何天柱 | Fruit sorting method |
| CN113177925A (en) * | 2021-05-11 | 2021-07-27 | 昆明理工大学 | Method for nondestructive detection of fruit surface defects |
| CN113177925B (en) * | 2021-05-11 | 2022-11-11 | 昆明理工大学 | Method for nondestructive detection of fruit surface defects |
| CN114160434A (en) * | 2021-12-09 | 2022-03-11 | 中通服供应链管理有限公司江西分公司 | Automatic dynamic sorting and carrying system |
| CN114160434B (en) * | 2021-12-09 | 2023-08-15 | 中通服供应链管理有限公司江西分公司 | Automatic system for dynamic sorting and carrying |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN2923067Y (en) | Multi-path fruit vision grading picture collector | |
| CN102284428B (en) | Corn real-time detection and grading machine vision system | |
| CN209174399U (en) | A kind of equipment of the pcb board sorting lamination of view-based access control model detection | |
| CN102941189B (en) | Controllable rotary angle insection tray device of fruit sorter | |
| CN210618577U (en) | Fruit sorting and size grading packaging system based on machine vision and PLC control | |
| CN101574693B (en) | Small-scale movable computer vision automatic navel orange separator | |
| CN201127937Y (en) | Material real-time detection system applying machine vision | |
| CN1329132C (en) | On-line fruit quality detection and classification apparatus and method based on three camera chains | |
| CN100569389C (en) | A kind of device for sizing spike-like fruits | |
| CN201364310Y (en) | PDC rock debris image automatic collecting instrument | |
| CN203705352U (en) | Magnetic shoe online detecting device based on machine vision | |
| CN110125021B (en) | Automatic silkworm cocoon sorting device | |
| CN201186270Y (en) | Multichannel fruit classification and separation system based on machine vision | |
| CN109433631A (en) | The integrated device that more sized bolt degree of injury detect and classify automatically | |
| CN108273764A (en) | A kind of intelligence fruit sorter | |
| CN202114018U (en) | Machine vision system for grain real-time detection and grading | |
| CN210742151U (en) | Detachable industrial part real-time detection device based on machine vision | |
| CN100365411C (en) | Detection method suited on surface of spherical fruit triggered to collect images based on need and equipment | |
| CN2774657Y (en) | Raisin sorter | |
| CN209565257U (en) | Engine commutator open defect automatic online vision inspection apparatus | |
| CN208513101U (en) | A kind of two-sided vision-based detection mango grading plant | |
| CN107442441A (en) | One kind machining uses mechanized classification device | |
| CN111661609A (en) | Safety monitoring equipment for Zongzi conveying by diversion mechanism and monitoring method thereof | |
| CN208786970U (en) | A kind of detection of glass and defective products rejecting mechanism | |
| CN110261160A (en) | A kind of eccentric wheel automatic sampler of view-based access control model detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20070718 Termination date: 20100621 |