CN106485204B - A kind of microballoon automatic capture method in optical optical tweezers system - Google Patents
A kind of microballoon automatic capture method in optical optical tweezers system Download PDFInfo
- Publication number
- CN106485204B CN106485204B CN201610832084.4A CN201610832084A CN106485204B CN 106485204 B CN106485204 B CN 106485204B CN 201610832084 A CN201610832084 A CN 201610832084A CN 106485204 B CN106485204 B CN 106485204B
- Authority
- CN
- China
- Prior art keywords
- particle
- path
- microballoon
- visual field
- background
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/693—Acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/752—Contour matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Manipulator (AREA)
Abstract
The present invention relates to a kind of microballoon automatic capture methods in optical optical tweezers system, comprising: setting image initial background；Preset path is scanned for according to path clustering micron displacement platform；To every frame image procossing, when there are microballoon, output microballoon positions, diameter, ID feature for visual field；It obtains in visual field after the feature of microballoon, interrupts searching route and generate capture path, PI closed-loop control is carried out according to the path of planning to particle, until particle is successfully captured, searching route is otherwise returned to and scans for；Judge whether particle is successfully captured；There are other extra particles near trapped particle, needs to generate and hide path.The present invention can greatly improve the capture rate of microballoon.
Description
Technical field
The present invention relates to a kind of microballoon automatic capture methods applied to optical tweezer measurement test macro.In particular to narrow
Microballoon automatic identification, the method for capture under visual field and low depth field imaging.
Background technique
Mechanics effect of the optical tweezer technology based on light can capture manipulation micron, nanoscale particle, and to the power applied
It measures, has the characteristics that non-contact, not damaged, high-precision, be widely used in the fields of measurement such as biologic single molecular, cell
In, greatly facilitate the development of quantitative biology.Optical tweezer technology mainly utilizes the laser beam of high order focusing to generate three-dimensional gesture
Trap calculates the active force being accordingly subject to generate attraction to fine particle, by measuring microballoon at a distance from ligh trap center.It is micro-
Ball is often uniformly distributed in sample cell, and traditional optical optical tweezers system lacks selectivity and exclusiveness when in use, attached in ligh trap
Close any dielectric particle is likely to be captured.Experimental test procedures are influenced to prevent from capturing multiple particles simultaneously, target
Sample must be dispersed in a liquid with low-down concentration.For the optical tweezer with semi-automatic operation is manually operated, generally require to spend
Take more time for microballoon capture above, greatly reduce conventional efficient, aggravated operator experiment burden.Optical tweezer skill
The emphasis of art automated thus become research.
The automatic technology of optical tweezer technology has many achievements and progress at present.Grover et al. utilizes image processing techniques
Realize a kind of single celled method of automatic sorting, Wu et al. realizes a kind of path of A* algorithm for unicellular carrying and advises
It draws.Equally, Banerjee et al. realizes a kind of free path planning algorithm for single celled carrying.Chapin et al. will be handed over
Drift then introduces the carrying of particle, realizes the arrangement of particle.CHeah et al. establishes the movement mould comprising particle Brownian movement
Type realizes a kind of for controlling the controller of Particles Moving.
The above research is most to establish in a kind of excessive ecotopia, such as clean, stable liquid environment.And it is more
It is directed to motion control arithmetic of the biggish particle such as cell under with larger field, required algorithm is applied for measurement
It is not much.For the optical optical tweezers system for power spectrometry, required particle diameter is smaller, generally in 1-2um or so；Required ligh trap
Rigidity it is higher, generally require to reach 0.5pn/nm, also mean that the object lens that use have higher numerical aperture, to make
Visual field and the depth of field, which must be observed, all becomes limited, and particle is finally made to repeat the phenomenon that capturing more easily generation.Simultaneously because rigidity
Promotion be also required to higher laser power, it is more obvious to also result in the heating effect in sample cell in this way, and result in sample
The convection current of liquid in product pond.Particle will also receive the influence of liquid environment convection current in addition to Brownian movement, so that targetedly capturing
Particle becomes more difficult.
Summary of the invention
The present invention provides a kind of automatic identification, capture 800nm-10um for big rigidity, the measurement test of the optical tweezer of small field of view
Fine particle, while preventing fine particle from repeating the control method of capture, can be in measurement test particle and biologic single molecular
Equal experimentations are automatically performed the more ball of catching of repetition and work, and the effective efficiency for improving experiment mitigates the workload of experimenter,
And promote the stability of experimental data.Technical scheme is as follows:
The technical scheme adopted by the invention is that:
A kind of microballoon automatic capture method in optical optical tweezers system, includes the following steps:
1) optical optical tweezers system initializes, and ligh trap position is arranged, and sets CCD time for exposure, frame per second, picture format, sets micro-nano
Rice displacement platform initial position, maximum movement speed, acceleration parameter；
2) image initial background is set；
3) preset path is scanned for according to path clustering micron displacement platform；
4) to every frame image procossing, when there are microballoon, output microballoon position, diameter, ID feature, specific steps packets for visual field
It includes:
(1) use background subtraction, remove the interference of background, background image need every 5 frames to background and present frame into
Average calculating operation of row removes the position of microballoon if there are microballoons for present frame as new background, then carries out more to background
Newly, background difference image is obtained；
(2) using global fixed threshold to background difference image binaryzation；
(3) Morphological scale-space method is used, closed operation is carried out to bianry image, obtains particle-filled pattern；
(4) extraction of particle profile and the fitting of profile circumscribed circle are carried out, the particle profile of single-frame images is tentatively obtained
Location information；
(5) after the first frame of acquisition contains particle picture, each particle is numbered, each particle obtains unique ID；
(6) process that particle extracts is repeated in next frame image, then by the radius of the particle of two images and position
Information is compared as feature vector, calculates the end-point distances of two feature vectors, and the smallest particle of end-point distances takes same
The particle for not finding matching result is taken new number by a ID, when the continuous frequency of occurrence of the particle of same ID reaches preset times,
Then think that the particle information is accurate and exports to outside module, otherwise it is assumed that being picture noise, and deletes the number and related letter
Breath；
5) it obtains in visual field after the feature of microballoon, interrupts searching route and generate capture path, to particle according to the road of planning
Diameter carries out PI closed-loop control, until particle is successfully captured, otherwise returns to searching route and scans for, capture the life in path
Include: at algorithm
(1) two delimited centered on two ligh traps in visual field and includes ligh trap and adjacent rectangular area, according to two
The positional relationship of rectangular area generates remaining several periphery rectangular area, so that visual field is divided into eight rectangular areas, then will
It numbers respectively each region；
(2) using the center of several periphery rectangular areas as key point, a figure by each key point is generated
Transfer path of the shape as particle；
(3) two ligh trap points are connected using horizontal line with vertical line with particle transfer path, and as particle into
Enter the connection path of ligh trap；
(4) it determines the rectangular area where intended particle position, is moved to the central point in the region, hence into transfer road
Diameter；
(5) the ligh trap target to be entered according to particle, according to nearby principle and the principle of preferential upper path, selection connects
Path is connect, and link road strength is entered by transfer path, by particle transfer to target ligh trap；
6) need to judge whether particle is successfully captured after trapped particle execution, judgment basis passes through where statistics ligh trap
The number of particle ID in rectangular area repeated, the rectangle where the particle of consecutive numbers frame ID is repetitively appearing in ligh trap
Region and change in location are less than certain threshold value, it is believed that particle is successfully captured；
7) when particle-capture determines successfully, then interrupt trap path is transferred to protected mode, is monitored to every frame image；When
Nearby there are other extra particles in trapped particle, needs to generate and hides path.
Preferably, the generating algorithm that path is hidden in 7) includes:
(1) if extra population be greater than one, select and ligh trap apart from nearest particle as preferentially target is hidden, be called
Intended particle；
(2) if intended particle is except movement routine enclosing region, nearby by horizontally or vertically moving or moving particle
Visual field out；
(3) if intended particle is within movement routine enclosing region, according to rectangular area where intended particle, just by particle
It is closely moved on transfer path, move mode is moved horizontally with vertical shift alternately according to the order of operated particle；
(4) determine inside region that movement routine is surrounded when there is no particle, by the extra particle in visual field it is horizontal nearby or
Outside vertical shift to visual field.
Manual operation bring mechanical oscillation can be eliminated relative to traditional manual capture and semi-automatic catching method
And the hysteresis of semi-automatic operation, the capture rate of microballoon can greatly be improved, reduces and repeats capture to experimental data
It destroys, guarantees the stability of experiment, be of great significance for the measurement based on optical optical tweezers system.
Detailed description of the invention
Fig. 1 is particle automatic capture control model flow chart
Fig. 2 is the flow chart of particle automatic identification track algorithm
Fig. 3 is particle-capture path planning algorithm schematic diagram
Fig. 4 is optical optical tweezers system structural schematic diagram.
In figure
1:1064nm Solid State Laser 2: beam system is closed in light beam polarization separation
3: binomial Look mirror 4: high-NA water immersion objective
5: piezoelectric nano displacement platform 6: servo micron displacement platform
7: sample cell 8: power spectral measurement system
9:780nmLED 10:COMS camera
Specific embodiment
The microballoon automatic capture method of the invention based on optical optical tweezers system is made in detail below with reference to embodiment and attached drawing
Explanation.
The test macro of this method is carried out using dual access test system shown in Fig. 4, including dual access test generation module, illumination
Module, image capture module and displacement platform control module.Dual access test generation module is used high using single laser (1064nm) beam splitting
NA objective convergence generates ligh trap；Lighting module uses transmission type coaxial Uniform Illumination, and lighting source uses 780nm wavelength
LED, illumination path and main optical path coupled using dichroscope, and image-forming module uses U.S. Thorlabs company
The COMS camera of DCC1545M, piezo controller (P-517.3CL) and the U.S. of the sample displacement platform platform using German PI Corp.
The TRA-12CC actuator of Newport company combines the control for carrying out three-dimensional.
The present invention carries out processing analysis using 8 gray level images of COMS camera acquisition particle, obtain particle position, half
The information such as diameter.The displacement method of control bit moving stage is formulated in the variation of comprehensive front and back particle state, is realized the automatic identification of microballoon, is caught
Obtain and trapped particle after prevent from repeating to capture, substantially increase the efficiency of measurement process, reduce shakiness caused by manual operation
It is qualitative with it is inefficient.
Microballoon automatic capture method based on optical optical tweezers system of the invention, as shown in Figure 1, including the following steps:
1) optical optical tweezers system initializes, and ligh trap position is arranged, and sets CCD time for exposure, frame per second, picture format, sets micro-nano
The parameters such as rice displacement platform initial position, maximum movement speed, acceleration；
2) image initial background is manually set or using default；
3) start automatic capture, automatically generate searching route (or manual preset path), be displaced according to path clustering micron
Platform scans for, and the generation method of specific searching route includes:
(1) polygon that automatic searching route is surrounded by key point is as region of search；
(2) region of search is traversed using serpentine path in region of search.
4) to every frame image procossing, when there are microballoon, output microballoon position, diameter, ID feature, specific process flows for visual field
As shown in Figure 2, comprising:
(1) use background subtraction, remove the interference of background, background image need every 5 frames to background and present frame into
Average calculating operation of row is as new background, since present frame can generally have microballoon, so need to remove the position of microballoon,
Background is updated again；
(2) using global fixed threshold to background difference image binaryzation；
(3) Morphological scale-space method is used, closed operation, obtained particle-filled pattern are carried out to bianry image；
(4) extraction of particle profile and the fitting of profile circumscribed circle are carried out according to Suzuki85 contours extract algorithm, just
Step obtains the particle outline position information of single-frame images；
(5) after the first frame of acquisition contains particle picture, each particle is numbered, each particle obtains unique ID；
(6) process that particle extracts is repeated in next frame image, then by the radius of the particle of two images and position
Information is compared as feature vector, calculates the end-point distances of two vectors, and the smallest particle of end-point distances takes the same ID,
The particle for not finding matching result is taken to new number.When the continuous frequency of occurrence of the particle of same ID reaches three times, then it is assumed that should
Particle information is accurate and exports to outside module, otherwise it is assumed that being picture noise, and deletes the number and relevant information.
5) it obtains in visual field after the feature of microballoon, interrupts searching route and generate capture path, to particle according to the road of planning
Diameter carries out PI closed-loop control, until particle is successfully captured.Otherwise it returns to searching route to scan for, captures the life in path
Include: at algorithm
(1) two delimited centered on two ligh traps in visual field and includes ligh trap and adjacent rectangular area, according to two
Upper and lower, left (right side) of rectangular area generates remaining six peripheries rectangular area, so that visual field is divided into eight rectangular areas, so
Each region is numbered respectively afterwards.
(2) using the center in six regions in periphery as key point, a rectangle by main points point is generated as particle
Transfer path.
(3) two ligh trap points are connected using horizontal line with vertical line with particle transfer path, and as particle into
Enter the connection path of ligh trap.
(4) it determines the rectangular area where intended particle position, is moved to the central point in the region, hence into transfer road
Diameter.
(5) the ligh trap target to be entered according to particle, according to nearby principle and the principle of preferential upper path, selection connects
Path is connect, and link road strength is entered by transfer path, by particle transfer to target ligh trap.
6) need to judge whether particle is successfully captured after trapped particle execution, judgment basis passes through where statistics ligh trap
The number of particle ID in rectangular area repeated, rectangular area and position where the particle of certain ID is repetitively appearing in ligh trap
It sets variation and is less than certain threshold value, be believed that particle is successfully captured after continuous 5 frame.
7) when particle-capture determines successfully, then interrupt trap path is transferred to protected mode, is monitored to every frame image.When
Nearby there are other particles in trapped particle, needs to generate and hides path.The generating algorithm for hiding path includes:
(1) if extra population is greater than one, select and ligh trap apart from nearest particle hides target as preferential.
(2) if intended particle is except movement routine enclosing region, nearby by horizontally or vertically moving or moving particle
Visual field out
(3) if intended particle is within movement routine enclosing region, according to rectangular area where intended particle, just by particle
It is closely moved on transfer path, move mode is moved horizontally with vertical shift alternately according to the order of operated particle.
(4) determine inside region that movement routine is surrounded when there is no particle, by the extra particle in visual field it is horizontal nearby or
Outside vertical shift to visual field.
Claims (2)
1. a kind of microballoon automatic capture method in optical optical tweezers system, includes the following steps:
1) optical optical tweezers system initializes, and ligh trap position is arranged, and sets CCD time for exposure, frame per second, picture format, sets micro-nano position
Moving stage initial position, maximum movement speed, acceleration parameter；
2) image initial background is set；
3) preset path is scanned for according to path clustering micron displacement platform；
4) to every frame image procossing, when there are microballoons for visual field, microballoon position, diameter, ID feature are exported, specific steps include:
(1) background subtraction is used, the interference of background is removed, background image needs to carry out one to background and present frame every 5 frames
Secondary average calculating operation is removed the position of microballoon, then be updated to background as new background if there are microballoons for present frame,
Obtain background difference image；
(2) using global fixed threshold to background difference image binaryzation；
(3) Morphological scale-space method is used, closed operation is carried out to bianry image, obtains particle-filled pattern；
(4) extraction of particle profile and the fitting of profile circumscribed circle are carried out, the particle outline position of single-frame images is tentatively obtained
Information；
(5) after the first frame of acquisition contains particle picture, each particle is numbered, each particle obtains unique ID；
(6) process that particle extracts is repeated in next frame image, then by the radius and location information of the particle of two images
It being compared as feature vector, calculates the end-point distances of two feature vectors, the smallest particle of end-point distances takes the same ID,
The particle for not finding matching result is taken to new number, when the continuous frequency of occurrence of the particle of same ID reaches preset times, is then recognized
Radius and location information for the particle are accurate and export to outside module, otherwise it is assumed that be picture noise, and delete the number with
And relevant information；
5) obtain in visual field after the feature of microballoon, interrupt searching route generate capture path, to particle according to planning path into
Otherwise row PI closed-loop control returns to searching route and scans for until particle is successfully captured, the generation for capturing path is calculated
Method includes:
(1) two delimited centered on two ligh traps in visual field and includes ligh trap and adjacent rectangular area, according to two rectangles
The positional relationship in region generates remaining several periphery rectangular area, so that visual field is divided into eight rectangular areas, it then will be each
It numbers respectively in region；
(2) it using the center of several periphery rectangular areas as key point, generates a figure by each key point and makees
For the transfer path of particle；
(3) two ligh trap points are connected using horizontal line with vertical line with particle transfer path, and enter light as particle
The connection path of trap；
(4) it determines the rectangular area where intended particle position, the central point in the region is moved to, hence into transfer path；
(5) the ligh trap target to be entered according to particle selects link road according to nearby principle and the principle of preferential upper path
Diameter, and connection path is entered by transfer path, by particle transfer to target ligh trap；
6) need to judge whether particle is successfully captured after trapped particle execution, judgment basis passes through rectangle where statistics ligh trap
The number of particle ID in region repeated, the rectangular area where the particle of consecutive numbers frame ID is repetitively appearing in ligh trap
And change in location is less than certain threshold value, it is believed that particle is successfully captured；
7) when particle-capture determines successfully, then interrupt trap path is transferred to protected mode, is monitored to every frame image；Work as capture
Nearby there are other extra particles in particle, needs to generate and hides path.
2. microballoon automatic capture method according to claim 1, which is characterized in that 7) hide the generating algorithm packet in path in
It includes:
(1) if extra population be greater than one, select and ligh trap apart from nearest particle as preferentially target is hidden, be called target
Particle；
(2) it if intended particle is except movement routine enclosing region, is regarded nearby by horizontally or vertically moving or removing particle
?；
(3) if intended particle is within movement routine enclosing region, according to rectangular area where intended particle, particle is moved nearby
It moves to transfer path, move mode is moved horizontally with vertical shift alternately according to the order of operated particle；
(4) it determines inside region that movement routine is surrounded when there is no particle, the extra particle in visual field is horizontal or vertical nearby
It is moved to outside visual field.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610832084.4A CN106485204B (en) | 2016-09-19 | 2016-09-19 | A kind of microballoon automatic capture method in optical optical tweezers system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610832084.4A CN106485204B (en) | 2016-09-19 | 2016-09-19 | A kind of microballoon automatic capture method in optical optical tweezers system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106485204A CN106485204A (en) | 2017-03-08 |
| CN106485204B true CN106485204B (en) | 2019-06-04 |
Family
ID=58268745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610832084.4A Active CN106485204B (en) | 2016-09-19 | 2016-09-19 | A kind of microballoon automatic capture method in optical optical tweezers system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106485204B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108917651B (en) * | 2018-07-06 | 2020-12-04 | 中国科学院光电技术研究所 | Super-resolution three-dimensional shape measurement method based on optical tweezers medium microspheres |
| CN109444047A (en) * | 2018-09-15 | 2019-03-08 | 天津大学 | A kind of efficient implementation method of unimolecule mechanical test |
| CN109239937A (en) * | 2018-09-15 | 2019-01-18 | 天津大学 | A kind of optical tweezer automation control device |
| CN110082282A (en) * | 2019-04-18 | 2019-08-02 | 天津大学 | The method and apparatus for realizing optical ultra-discrimination imaging based on optical tweezer |
| CN111750778B (en) * | 2020-07-01 | 2021-04-20 | 浙江大学 | Particle position detection device based on double-optical-tweezers system and precision improvement method |
| CN114077168B (en) * | 2022-01-06 | 2022-06-03 | 之江实验室 | Super-resolution laser direct writing and real-time imaging device and method based on optical tweezers microspheres |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102285630A (en) * | 2011-05-06 | 2011-12-21 | 中国科学技术大学苏州研究院 | Automatic particle handing method based on optical tweezers |
| CN103674814A (en) * | 2012-09-13 | 2014-03-26 | 香港城市大学 | Methods and means for manipulating particles |
| CN105931202A (en) * | 2016-04-20 | 2016-09-07 | 广州华端科技有限公司 | Geometric correction die body correction method and system |
-
2016
- 2016-09-19 CN CN201610832084.4A patent/CN106485204B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102285630A (en) * | 2011-05-06 | 2011-12-21 | 中国科学技术大学苏州研究院 | Automatic particle handing method based on optical tweezers |
| CN103674814A (en) * | 2012-09-13 | 2014-03-26 | 香港城市大学 | Methods and means for manipulating particles |
| CN105931202A (en) * | 2016-04-20 | 2016-09-07 | 广州华端科技有限公司 | Geometric correction die body correction method and system |
Non-Patent Citations (5)
| Title |
|---|
| Developping a video tracking method to study interactions between close pairs of optically trapped particles in three dimensions;ALLAN RAUDSEPP 等;《Applied Optics》;20151110;第54卷(第32期);9518-9527 |
| Tapered fiber optical tweezers for microscopic particle trapping:fabrication and application;Zhihai Liu 等;《Optics Express》;20061211;第14卷(第25期);12510-12516 |
| 利用改进的粒子群算法的机器人全局路径规划;薛英花 等;《华中科技大学学报（自然科学版）》;20081031;第36卷;167-170 |
| 基于HPSO算法的三维空间路径规划;陈世明 等;《华中科技大学学报（自然科学版）》;20130228;第41卷(第2期);109-113+119 |
| 荧光标记聚苯乙烯微球的激光捕获及其原位稳态和时间分辨荧光光谱研究;李明 等;《影像科学与光化学》;20101130;第28卷(第6期);416-424 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106485204A (en) | 2017-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106485204B (en) | A kind of microballoon automatic capture method in optical optical tweezers system | |
| CN103998177B (en) | The welding position checkout gear of laser weld and welding position detection method | |
| CN103674814B (en) | Method and apparatus for operating particle | |
| Huang et al. | Optoelectronic tweezers integrated with lensfree holographic microscopy for wide-field interactive cell and particle manipulation on a chip | |
| JPWO2019180848A1 (en) | Cell image analyzer, cell image analysis system, training data generation method, training model generation method, training data generation program, and training data manufacturing method | |
| JP6160187B2 (en) | Analysis device, analysis program, and analysis system | |
| JP2010530809A (en) | Machining system control apparatus and method | |
| WO2022160772A1 (en) | Person re-identification method based on view angle guidance multi-adversarial attention | |
| KR20220095216A (en) | BBP-assisted defect detection flow for SEM images | |
| CN113369697B (en) | Laser polishing online detection system and method | |
| JP2010004789A (en) | Embryo observation apparatus | |
| CN110793946A (en) | Fungus sample microscopic imaging and intelligent identification system and method | |
| JP7277886B2 (en) | AUTONOMOUS MICROSCOPE SYSTEM CONTROL METHOD, MICROSCOPE SYSTEM AND COMPUTER-READABLE STORAGE MEDIUM | |
| Xiang et al. | Autofocus of whole slide imaging based on convolution and recurrent neural networks | |
| JP6548965B2 (en) | Microscope system and microscopic observation method | |
| Arun et al. | Effective and efficient multi-crop pest detection based on deep learning object detection models | |
| Serhan et al. | Push-to-see: learning non-prehensile manipulation to enhance instance segmentation via deep q-learning | |
| CN112750118B (en) | Novel method and system for identifying cell number in single cell pore plate sequencing based on automatic visual detection | |
| CN102285630A (en) | Automatic particle handing method based on optical tweezers | |
| Kitrungrotsakul et al. | A cascade of CNN and LSTM network with 3D anchors for mitotic cell detection in 4D microscopic image | |
| Pan et al. | A searching space constrained partial to full registration approach with applications in airport trolley deployment robot | |
| WO2001071663A1 (en) | Cell lineage extracting method | |
| Yin et al. | A novel automatic classification approach for micro-flaws on the large-aperture optics surface based on multi-light source fusion and integrated deep learning architecture | |
| Ren et al. | Machine learning-based real-time localization and automatic trapping of multiple microrobots in optical tweezer | |
| CN106023191A (en) | Optical drawing character edge extraction and edge fitting method based on structure features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |