CN104897671B - A kind of identifying system of fruit carpopodium calyx - Google Patents
A kind of identifying system of fruit carpopodium calyx Download PDFInfo
- Publication number
- CN104897671B CN104897671B CN201510230771.4A CN201510230771A CN104897671B CN 104897671 B CN104897671 B CN 104897671B CN 201510230771 A CN201510230771 A CN 201510230771A CN 104897671 B CN104897671 B CN 104897671B
- Authority
- CN
- China
- Prior art keywords
- fruit
- image
- height
- laser
- transmission 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.)
- Active
Links
Abstract
The present invention discloses a kind of identifying system of fruit carpopodium calyx, including：CCD camera, the computer being connect with CCD camera, linear array diode laser, transmission device and at least one light source；Wherein, the identical height above the center line of transmission device is arranged with linear array diode laser in CCD camera, and the plane that the center line of CCD camera, linear array diode laser and transmission device is constituted is perpendicular to transmission device；The central axis of laser lines and transmission device that the laser that linear array diode laser is sent out is formed on transmission device, and laser lines are in the underface of CCD camera；Light source provides illumination for the fruit on transmission device；Computer, the fruit image for receiving CCD camera acquisition, and according to fruit image, identify fruit carpopodium calyx.The system of the present invention overcomes the complexity that mechanical device localization method determines carpopodium calyx, avoids the required repetition training of mode identification method identification carpopodium calyx and the coding and decoding operation of lattice structure light technical sophistication.
Description
Technical field
The present invention relates to agricultural product test technique automatic fields, and in particular to a kind of identification system of fruit carpopodium calyx
System.
Background technology
External Defect is that fruit (such as apple) quality the most intuitively reflects.Currently, machine vision technique is answered extensively
In detection for fruit external sort.After the surface image that camera collects fruit, be transmitted to computer, then by image at
The method of reason obtains the external sorts features such as size, shape, color, the defect of fruit, and then according to the standard pair of sorted fruits
Fruit carries out classification processing.Take apple as an example, apple sorting equipment can be carried out according to the size, color, shape of apple at present
Automation sorting.However since the carpopodium calyx of apple is much like with defect in color and texture, therefore apple quality sorting is set
It is standby to be detected sorting according to the surface defect of apple.In terms of identification carpopodium calyx and defect, mainly pass through machine
Tool localization method, mode identification method and lattice structure light method.
Carpopodium calyx recognition methods based on machinery positioning is to increase assist, and apple is adjusted by mechanical device
Posture, make the carpopodium calyx of apple orientation have fixed known location.Such mechanical device is more complicated, is unfavorable for
The quick identification and positioning of apple stem calyx.
Mode based on pattern-recognition is to carry out the selection and extraction of feature before detection, then trains grader to realize
To the discriminant classification of carpopodium calyx and defect mode.However the method based on pattern-recognition needs repetition training grader, and
Grader is highly dependent on the conditions such as selected feature and illumination.
Apple stem calyx recognition methods based on lattice structure light is by the structure light of dot matrix being played the table in apple
Face, according to the variation identification carpopodium and calyx of dot matrix.Method based on lattice structure light needs to carry out the dot matrix of structure light
Coding and decoding, operand are larger.
Invention content
The technical problem to be solved by the present invention is to how reduce mechanical device localization method to determine the complexity of carpopodium calyx
Property, avoid the mode identification method required repetition training of identification carpopodium calyx and reduce the volume of lattice structure light technical sophistication
The problem of code decoding operation.
For this purpose, the present invention proposes a kind of identifying system of fruit carpopodium calyx, including：CCD camera and CCD camera
Computer, linear array diode laser, transmission device and at least one light source of connection；
Wherein, the CCD camera is arranged identical above the center line of the transmission device with the linear array diode laser
Highly, and the plane of the center line of the CCD camera, linear array diode laser and transmission device composition is perpendicular to the transmission device；
Wherein, the laser lines that the laser that the linear array diode laser is sent out is formed on the transmission device and the transmission
The central axis of device, and the laser lines are in the underface of the CCD camera；
Wherein, the light source provides illumination for the fruit on the transmission device；
Wherein, the computer, the fruit image for receiving CCD camera acquisition, and according to the fruit image,
Identify the fruit carpopodium calyx, wherein the fruit image is the laser rays that the laser lines are formed on the fruit
Image.
Optionally, the computer, including：
Receiving unit, the fruit image for receiving the CCD camera acquisition；The fruit image is the laser lines
The laser line image formed on the fruit；
Recognition unit, the fruit image for being received according to the receiving unit, identifies the fruit carpopodium calyx.
Optionally, the recognition unit, including：
Fruit height obtains subelement, for handling rule according to pre-set image, obtains the water that the receiving unit receives
The Pixel Information and range information of fruit image, and obtain according to the Pixel Information and range information the height of the fruit；
Fruit height draws subelement, for obtaining the fruit height that subelement obtains according to the fruit height, draws
Fruit height image；
Carpopodium calyx identifies subelement, for drawing the fruit height image that subelement is drawn according to the fruit height,
Identify fruit carpopodium calyx.
Optionally, the height h that the fruit height acquisition subelement obtains the fruit meets following formula：
Wherein, the intersecting lens that the laser that h sends out for fruit surface and the linear array diode laser is crossed to form is apart from the biography
Send the maximum height of device；L is height of the CCD camera apart from the transmission device；S is the linear array diode laser and described
The distance between CCD camera；D is the intersection point distance that the CCD camera intersects with the extended line of P point lines and the transmission device
The distance of datum line；
Wherein, described in the intersecting lens distance that P points are crossed to form for fruit surface with the laser that the linear array diode laser is sent out
The corresponding position of maximum height of transmission device；
Wherein, the laser rays that the datum line is formed for the laser that the linear array diode laser is sent out on the transmission device
Position where item；
Wherein, d obtains subelement by the fruit height and is obtained according to pre-set image processing rule.
Optionally, the carpopodium calyx identifies subelement, is specifically used for：
The fruit height image that subelement is drawn is drawn according to the fruit height, seeks the maximum in fruit height image
The luminance quantization value of height value and minimum height values；
To the fruit height draw subelement draw fruit height image carry out binary segmentation, obtain fruit where
Region Mask images；
The minimum circumscribed circle of the region Mask images is sought, and records the center of circle O and radius R of minimum circumscribed circle；
All pixels point brightness value is zero in newly-built initial pictures Con, the initial pictures Con；
In the initial pictures Con, the luminance quantization value of the maximum height value is set as the brightness of the center of circle O
Value, sets the luminance quantization value of minimum height values as the brightness value of pixel on annulus at radius R, obtains the first image Con；
Using O as the center of circle, using a pixel as step-length, donut, the same radius are constructed on described first image Con
Annulus on pixel height having the same, i.e., brightness value having the same obtains the second image Con；
Median filter process is carried out to the second image Con, fills the gap between annulus in the second image Con
Point obtains third image Con；
Processing is masked to the third image Con, obtains the 4th image Con, the 4th image Con connects with described
Receive the fruit image boundary shape having the same that unit receives；
The fruit height is drawn into the fruit height image divided by the 4th image Con that subelement is drawn, then again
It is multiplied by 255 acquisition ratio images Ratio；
Divide rule according to preset single threshold, to ratio images Ratio extraction carpopodium calyx region.
Compared with the prior art, the identifying system of fruit carpopodium calyx of the invention is a kind of fruit based on machine vision
The identifying system of (such as apple) carpopodium calyx is related to agricultural product appearance quality detection field, and take apple as an example, which passes through line
Battle array laser and area array cameras obtain the height map of apple on conveyer belt, and image processing algorithm is then utilized to build one and obtain
Height map have identical boundary shape height rebuild figure, then utilize than value-based algorithm realize carpopodium calyx identification.This hair
The bright complexity for overcoming mechanical device localization method and determining carpopodium calyx avoids mode identification method identification carpopodium calyx institute
The repetition training needed, and avoid the coding and decoding operation of lattice structure light technical sophistication.The present invention can be simple and quick
Realization carpopodium calyx identification, apple external sort detection in have larger application potential.
Description of the drawings
Fig. 1 is a kind of identifying system structure chart of fruit carpopodium calyx provided in an embodiment of the present invention；
Fig. 2 is the schematic diagram of the height h provided in an embodiment of the present invention for obtaining fruit.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not having
The every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
As shown in Figure 1, the present embodiment discloses a kind of identifying system of fruit carpopodium calyx, which may include：CCD camera
1, computer 2, linear array diode laser 3, transmission device 4 and at least one light source 5 being connect with CCD camera 1.
The system of the present embodiment includes two light sources 5, provides illumination for the fruit on transmission device 4, and light source 5 is
The paster LED being linearly distributed.
In the present embodiment, the identical height above the center line of transmission device 4 is arranged with linear array diode laser 3 for CCD camera 1
Degree, and the plane that the center line of CCD camera 1, linear array diode laser 3 and transmission device 4 is constituted is perpendicular to transmission device 4.
In the present embodiment, laser lines that laser that linear array diode laser 3 is sent out is formed on transmission device 4 (and in Fig. 1
Datum line overlaps) with the central axis of transmission device 4, and the laser lines are in the underface of CCD camera 1；Specifically, line
The conveyer belt for the laser plane and transmission device 4 that the laser that battle array laser 3 is sent out is constituted is crossed to form laser lines.
In the present embodiment, computer 2, the fruit image for receiving the acquisition of CCD camera 1, and according to fruit image, identification
The fruit carpopodium calyx, wherein the fruit image is the laser lines figure that the laser lines are formed on the fruit
Picture.
In a specific example, computer 2, including：Receiving unit and recognition unit；
Wherein, receiving unit, the fruit image for receiving the acquisition of CCD camera 1；The fruit image is the laser rays
The laser line image that item is formed on the fruit；
Wherein, recognition unit, the fruit image for being received according to receiving unit, identifies the fruit carpopodium calyx.
In a specific example, recognition unit, including：Fruit height obtains subelement, fruit height draws son list
Member and carpopodium calyx identify subelement；
Wherein, fruit height obtains subelement, for handling rule according to pre-set image, obtains the receiving unit and receives
Fruit image Pixel Information and range information, and obtain according to the Pixel Information and range information the height of the fruit
Degree；
Wherein, fruit height draws subelement, for obtaining the fruit height that subelement obtains according to the fruit height,
Draw fruit height image；
Wherein, carpopodium calyx identifies subelement, for drawing the fruit height that subelement is drawn according to the fruit height
Image identifies fruit carpopodium calyx.
In a specific example, as shown in Figure 2 (for convenience of describing, the fruit shape in this example is rectangular), institute
It states fruit height and obtains subelement and obtain the height h of the fruit and meet following formula：
Wherein, h is that the intersecting lens that fruit surface is crossed to form with the laser that linear array diode laser 3 is sent out is filled apart from the transmission
Set 4 maximum height；L is height of the CCD camera 1 apart from transmission device 4；S between linear array diode laser 3 and CCD camera 1 away from
From；D is distance of the intersection point that intersects with transmission device 4 of CCD camera 1 and the extended line of P point lines apart from datum line；The benchmark
Line is the position where the laser lines that the laser that linear array diode laser 3 is sent out is formed on transmission device 4；
Wherein, the intersecting lens that the laser that P points send out for fruit surface and linear array diode laser 3 is crossed to form is apart from transmission device
The 4 corresponding position of maximum height；
Wherein, d obtains subelement by the fruit height and is obtained according to pre-set image processing rule.
In a specific example, the carpopodium calyx identifies subelement, is specifically used for：
S1, the fruit height image that subelement is drawn is drawn according to the fruit height, sought in fruit height image
The luminance quantization value of maximum height value and minimum height values；
S2, the fruit height image progress binary segmentation that subelement is drawn is drawn to the fruit height, obtain fruit institute
Region Mask images；
S3, the minimum circumscribed circle for seeking the region Mask images, and record the center of circle O and radius R of minimum circumscribed circle；
All pixels point brightness value is zero in S4, newly-built initial pictures Con, the initial pictures Con；
S5, in the initial pictures Con, set the luminance quantization value of the maximum height value as the bright of the center of circle O
Angle value sets the luminance quantization value of minimum height values as the brightness value of pixel on annulus at radius R, obtains the first image Con；
S6, using O as the center of circle, using a pixel as step-length, donut is constructed on described first image Con, it is same
Pixel height having the same on the annulus of radius, i.e., brightness value having the same obtain the second image Con；
S7, median filter process is carried out to the second image Con, filled in the second image Con between annulus
Gap point obtains third image Con；
S8, processing is masked to the third image Con, obtains the 4th image Con, the 4th image Con and institute
State the fruit image boundary shape having the same of receiving unit reception；
S9, the fruit height is drawn into the fruit height image divided by the 4th image Con that subelement is drawn, then
Ratio images Ratio is obtained multiplied by with 255；
S10, rule is divided according to preset single threshold, to ratio images Ratio extraction carpopodium calyx region.This reality
It applies the segmentation of the single threshold in example rule and existing single threshold dividing method can be used, the present embodiment is no longer described in detail.
The identifying system of above-mentioned fruit carpopodium calyx, when not having fruit in 1 underface of CCD camera, CCD camera 1 is adopted
The laser lines integrated is straight lines；When fruit is in 1 underface of CCD camera, due between linear array diode laser 3 and CCD camera 1
With a certain distance s, therefore the laser lines that CCD camera 1 is acquired are a curve.Fruit height is higher, CCD camera 1
It is more apparent that the laser lines acquired deviate datum line (linear position in the presence of no object).
The elevation information of fruit can be sought according to triangle analogue method using distance s.It is obtained first with CCD camera 1
The image of laser lines refines image using image processing method, seeks being adopted by CCD camera 1 caused by distance s
Then the Pixel Information and range information of deviation between the laser lines and datum line of collection utilize Similar Principle of Triangle, ask
Take height.Relational expression is：
L is known quantity, can be measured；S is known quantity, can be measured.
For entire fruit, it may be by above-mentioned triangle similarity relation and seek corresponding height information.With conveyer belt
Transmission, fruit is progressively scanned, then can obtain the elevation information at apple every bit, i.e. height map.
For apple, the carpopodium calyx of apple has the feature of recess, therefore human eye can be according to the recess in height map
It is easy to judge carpopodium calyx.However the edge of apple also has relatively low height, in order to make computer quickly identify
Carpopodium calyx, the carpopodium calyx in computer identify subelement, execute following step S1 to S10：
S1, the fruit height image that subelement is drawn is drawn according to the fruit height, sought in fruit height image
The luminance quantization value of maximum height value and minimum height values；
S2, the fruit height image progress binary segmentation that subelement is drawn is drawn to the fruit height, obtain fruit institute
Region Mask images；
S3, the minimum circumscribed circle for seeking the region Mask images, and record the center of circle O and radius R of minimum circumscribed circle；
All pixels point brightness value is zero in S4, newly-built initial pictures Con, the initial pictures Con；
S5, in the initial pictures Con, set the luminance quantization value of the maximum height value as the bright of the center of circle O
Angle value sets the luminance quantization value of minimum height values as the brightness value of pixel on annulus at radius R, obtains the first image Con；
S6, using O as the center of circle, using a pixel as step-length, donut is constructed on described first image Con, it is same
Pixel height having the same on the annulus of radius r, i.e., brightness value having the same obtain the second image Con；Wherein, half
Diameter is that the brightness value calculation formula of the pixel on the annulus of r is：
Wherein：IintensityFor the brightness value that radius is the pixel on the annulus of r；Max is the amount of brightness of maximum height value
Change value；Min is the luminance quantization value of minimum height values；
S7, median filter process is carried out to the second image Con, filled in the second image Con between annulus
Gap point obtains third image Con；
S8, processing is masked to the third image Con, obtains the 4th image Con, the 4th image Con and institute
State the fruit image boundary shape having the same of receiving unit reception；
S9, the fruit height is drawn into the fruit height image divided by the 4th image Con that subelement is drawn, then
Ratio images Ratio is obtained multiplied by with 255；By the notch characteristic of carpopodium calyx, in the height image of apple, carpopodium calyx is in
Existing lower brightness, and the height image built does not account for the presence of carpopodium calyx, corresponding position pixel brightness value does division
After operation, lower brightness value will be presented in (low-light level is removed in high brightness) at carpopodium calyx, remaining position (similar luminance value phase
Except) higher brightness value is then presented.
S10, rule is divided according to preset single threshold, to ratio images Ratio extraction carpopodium calyx region.This reality
It applies the segmentation of the single threshold in example rule and existing single threshold dividing method can be used, the present embodiment is no longer described in detail.
It will be appreciated by those of skill in the art that although some embodiments described herein include being wrapped in other embodiments
Certain features for including rather than other feature, but the combination of the feature of different embodiments mean in the scope of the present invention it
It is interior and form different embodiments.
Although the embodiments of the invention are described in conjunction with the attached drawings, but those skilled in the art can not depart from this hair
Various modifications and variations are made in the case of bright spirit and scope, such modifications and variations are each fallen within by appended claims
Within limited range.
Claims (2)
1. a kind of identifying system of fruit carpopodium calyx, which is characterized in that including：CCD camera, the calculating being connect with CCD camera
Machine, linear array diode laser, transmission device and at least one light source；
Wherein, the identical height above the center line of the transmission device is arranged with the linear array diode laser in the CCD camera,
And the plane that the center line of the CCD camera, linear array diode laser and transmission device is constituted is perpendicular to the transmission device；
Wherein, the laser lines that the laser that the linear array diode laser is sent out is formed on the transmission device and the transmission device
Central axis, and the laser lines are in the underface of the CCD camera；
Wherein, the light source provides illumination for the fruit on the transmission device；
Wherein, the computer, the fruit image for receiving the CCD camera acquisition, and according to the fruit image, identification
The fruit carpopodium calyx, wherein the fruit image is the laser lines figure that the laser lines are formed on the fruit
Picture；
The computer includes receiving unit and recognition unit, and receiving unit is used to receive the fruit figure of the CCD camera acquisition
Picture；The fruit image is the laser line image that the laser lines are formed on the fruit；Recognition unit is used for basis
The fruit image that the receiving unit receives, identifies the fruit carpopodium calyx；
The recognition unit includes that fruit height obtains subelement, fruit height draws subelement and carpopodium calyx identification is single
Member, wherein：
Fruit height obtains subelement, for handling rule according to pre-set image, obtains the fruit figure that the receiving unit receives
The Pixel Information and range information of picture, and obtain according to the Pixel Information and range information the height of the fruit；
Fruit height draws subelement, for obtaining the fruit height that subelement obtains according to the fruit height, draws fruit
Height image；
The carpopodium calyx identifies subelement, is specifically used for：
The fruit height image that subelement is drawn is drawn according to the fruit height, seeks the maximum height in fruit height image
The luminance quantization value of value and minimum height values；
The fruit height image that subelement is drawn is drawn to the fruit height and carries out binary segmentation, obtains the region where fruit
Mask images；
The minimum circumscribed circle of the region Mask images is sought, and records the center of circle O and radius R of minimum circumscribed circle；
All pixels point brightness value is zero in newly-built initial pictures Con, the initial pictures Con；
In the initial pictures Con, the luminance quantization value of the maximum height value is set as the brightness value of the center of circle O, if
The luminance quantization value for determining minimum height values is the brightness value of pixel on annulus at radius R, obtains the first image Con；
Using O as the center of circle, using a pixel as step-length, donut, the circle of the same radius are constructed on described first image Con
Pixel height having the same on ring, i.e., brightness value having the same obtain the second image Con；
Median filter process is carried out to the second image Con, fills the gap point between annulus in the second image Con,
Obtain third image Con；
Processing is masked to the third image Con, obtains the 4th image Con, the 4th image Con is single with the reception
The fruit image boundary shape having the same that member receives；
By the fruit height draw subelement draw fruit height image divided by the 4th image Con, then multiplied by with
255 obtain ratio images Ratio；
Divide rule according to preset single threshold, to ratio images Ratio extraction carpopodium calyx region.
2. system according to claim 1, which is characterized in that the fruit height obtains subelement and obtains the fruit
Height h meets following formula：
Wherein, h is that the intersecting lens that fruit surface is crossed to form with the laser that the linear array diode laser is sent out is filled apart from the transmission
The maximum height set；L is height of the CCD camera apart from the transmission device；S is the linear array diode laser and the CCD
The distance between camera；D is the intersection point that intersects with the transmission device of the CCD camera and the extended line of P point lines apart from base
The distance of directrix；
Wherein, the intersecting lens that the laser that P points send out for fruit surface and the linear array diode laser is crossed to form is apart from the transmission
The corresponding position of maximum height of device；
Wherein, the laser lines institute that the datum line is formed for the laser that the linear array diode laser is sent out on the transmission device
Position；
Wherein, d obtains subelement by the fruit height and is obtained according to pre-set image processing rule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510230771.4A CN104897671B (en) | 2015-05-07 | 2015-05-07 | A kind of identifying system of fruit carpopodium calyx |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510230771.4A CN104897671B (en) | 2015-05-07 | 2015-05-07 | A kind of identifying system of fruit carpopodium calyx |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104897671A CN104897671A (en) | 2015-09-09 |
| CN104897671B true CN104897671B (en) | 2018-09-11 |
Family
ID=54030472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510230771.4A Active CN104897671B (en) | 2015-05-07 | 2015-05-07 | A kind of identifying system of fruit carpopodium calyx |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104897671B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108801942B (en) * | 2018-03-01 | 2020-07-24 | 上海交通大学 | Linear array laser imaging method for rice tillering counting |
| CN108445003B (en) * | 2018-03-19 | 2021-05-18 | 烟台大学 | Fruit quality detection device and detection method |
| CN109489572B (en) * | 2018-12-28 | 2020-08-11 | 浙江农林大学 | Automobile air conditioner piston inner spherical surface diameter detection device |
| CN109650009B (en) * | 2019-02-02 | 2020-11-03 | 塔里木大学 | Bergamot pear azimuth angle adjusting device and method |
| CN110495624A (en) * | 2019-08-29 | 2019-11-26 | 贵州大学 | A kind of fruit based on image recognition removes speed governor |
| CN111811416A (en) * | 2020-06-28 | 2020-10-23 | 江苏理工学院 | Device and method for detecting height difference of plane of cooling fan |
| CN111811417B (en) * | 2020-06-28 | 2022-03-25 | 江苏理工学院 | Large-height-difference stepped shaft detection device and detection method |
| CN113051992B (en) * | 2020-11-16 | 2022-01-18 | 山东米捷软件有限公司 | Uniform speed identification system applying transparent card slot |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102854192B (en) * | 2012-08-22 | 2014-11-19 | 北京农业智能装备技术研究中心 | Method for detecting apple surface defect based on apple surface defect detecting system |
| CN103697833B (en) * | 2013-12-30 | 2016-03-09 | 北京农业智能装备技术研究中心 | Agricultural product shape detecting method and device |
| CN104569154B (en) * | 2015-01-04 | 2017-06-13 | 浙江大学 | The detection method and device of quick nondestructive fruit quality |
-
2015
- 2015-05-07 CN CN201510230771.4A patent/CN104897671B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN104897671A (en) | 2015-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104897671B (en) | A kind of identifying system of fruit carpopodium calyx | |
| DE102015104732B4 (en) | INFORMATION PROCESSING DEVICE, METHOD FOR CONTROLLING AN INFORMATION PROCESSING DEVICE, GRIPPING SYSTEM AND STORAGE MEDIUM | |
| US10558844B2 (en) | Lightweight 3D vision camera with intelligent segmentation engine for machine vision and auto identification | |
| Sulami et al. | Automatic recovery of the atmospheric light in hazy images | |
| CN105682310B (en) | Combined lighting device and method based on image quality control | |
| CN107705288A (en) | Hazardous gas spillage infrared video detection method under pseudo- target fast-moving strong interferers | |
| WO2021051604A1 (en) | Method for identifying text region of osd, and device and storage medium | |
| CN104597057B (en) | A kind of column Diode facets defect detecting device based on machine vision | |
| CN104239909B (en) | A kind of recognition methods of image and device | |
| CN110084243B (en) | File identification and positioning method based on two-dimensional code and monocular camera | |
| CN104361353A (en) | Application of area-of-interest positioning method to instrument monitoring identification | |
| CN106651882B (en) | A kind of bird's nest impurities identification and detection method and device based on machine vision | |
| CN106991654A (en) | Human body beautification method and apparatus and electronic installation based on depth | |
| CN108288289B (en) | LED visual detection method and system for visible light positioning | |
| CN109961399B (en) | Optimal suture line searching method based on image distance transformation | |
| CN109523551B (en) | Method and system for acquiring walking posture of robot | |
| Hannan et al. | A real-time machine vision algorithm for robotic citrus harvesting | |
| CN111292228A (en) | Lens defect detection method | |
| CN110413122B (en) | AR (augmented reality) glasses application method and system with working scene recognition function | |
| CN102043963A (en) | Method for recognizing and counting number of people in image | |
| CN108198226B (en) | Ceramic color identification method, electronic equipment, storage medium and device | |
| CN105758337B (en) | A method of obtaining angle between lens plane and image sensor plane | |
| CN106204889B (en) | A kind of localization method and device of bank note fluorescence area | |
| CN106204648B (en) | A kind of method for tracking target and device rejected based on background | |
| CN107705302A (en) | A kind of circular and similar round visible detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 1107, block a, Nongke building, No. 11, Shuguang garden middle road, Haidian District, Beijing, 100097 Patentee after: Intelligent equipment technology research center of Beijing Academy of agricultural and Forestry Sciences Address before: 318b, block a, Beijing Agricultural Science Building, 11 Shuguang Huayuan Middle Road, Haidian District, Beijing 100097 Patentee before: BEIJING RESEARCH CENTER OF INTELLIGENT EQUIPMENT FOR AGRICULTURE |
|
| CP03 | Change of name, title or address |