The Improved SVM Multi Objects' Identification For the Uncalibrated Visual Servoing
For the assembly of multi micro objects in micromanipulation, the first task is to identify multi micro parts. We present an improved support vector machine algorithm, which employs invariant moments based edge extraction to obtain feature attribute and then presents a heuristic attribute reduction...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2009-03-01
|
| Series: | International Journal of Advanced Robotic Systems |
| Subjects: | |
| Online Access: | http://www.intechopen.com/articles/show/title/the_improved_svm_multi_objects__identification_for_the_uncalibrated_visual_servoing |
| _version_ | 1818142620215410688 |
|---|---|
| author | Min Wang Xiangjin Zeng Xinhan Huang |
| author_facet | Min Wang Xiangjin Zeng Xinhan Huang |
| author_sort | Min Wang |
| collection | DOAJ |
| description | For the assembly of multi micro objects in micromanipulation, the first task is to identify multi micro parts. We present an improved support vector machine algorithm, which employs invariant moments based edge extraction to obtain feature attribute and then presents a heuristic attribute reduction algorithm based on rough set's discernibility matrix to obtain attribute reduction, with using support vector machine to identify and classify the targets. The visual servoing is the second task. For avoiding the complicated calibration of intrinsic parameter of camera, We apply an improved broyden's method to estimate the image jacobian matrix online, which employs chebyshev polynomial to construct a cost function to approximate the optimization value, obtaining a fast convergence for online estimation. Last, a two DOF visual controller based fuzzy adaptive PD control law for micro-manipulation is presented. The experiments of micro-assembly of micro parts in microscopes confirm that the proposed methods are effective and feasible. |
| first_indexed | 2024-12-11T11:18:40Z |
| format | Article |
| id | doaj.art-69b22f4e385f4fa8b3bedea3d477fd10 |
| institution | Directory Open Access Journal |
| issn | 1729-8806 1729-8814 |
| language | English |
| last_indexed | 2024-12-11T11:18:40Z |
| publishDate | 2009-03-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | International Journal of Advanced Robotic Systems |
| spelling | doaj.art-69b22f4e385f4fa8b3bedea3d477fd102022-12-22T01:09:14ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88061729-88142009-03-0161The Improved SVM Multi Objects' Identification For the Uncalibrated Visual ServoingMin WangXiangjin ZengXinhan HuangFor the assembly of multi micro objects in micromanipulation, the first task is to identify multi micro parts. We present an improved support vector machine algorithm, which employs invariant moments based edge extraction to obtain feature attribute and then presents a heuristic attribute reduction algorithm based on rough set's discernibility matrix to obtain attribute reduction, with using support vector machine to identify and classify the targets. The visual servoing is the second task. For avoiding the complicated calibration of intrinsic parameter of camera, We apply an improved broyden's method to estimate the image jacobian matrix online, which employs chebyshev polynomial to construct a cost function to approximate the optimization value, obtaining a fast convergence for online estimation. Last, a two DOF visual controller based fuzzy adaptive PD control law for micro-manipulation is presented. The experiments of micro-assembly of micro parts in microscopes confirm that the proposed methods are effective and feasible.http://www.intechopen.com/articles/show/title/the_improved_svm_multi_objects__identification_for_the_uncalibrated_visual_servoingMicro-assemblySupport vector machineMulti parts identificationBroyden methodVisual servoing |
| spellingShingle | Min Wang Xiangjin Zeng Xinhan Huang The Improved SVM Multi Objects' Identification For the Uncalibrated Visual Servoing International Journal of Advanced Robotic Systems Micro-assembly Support vector machine Multi parts identification Broyden method Visual servoing |
| title | The Improved SVM Multi Objects' Identification For the Uncalibrated Visual Servoing |
| title_full | The Improved SVM Multi Objects' Identification For the Uncalibrated Visual Servoing |
| title_fullStr | The Improved SVM Multi Objects' Identification For the Uncalibrated Visual Servoing |
| title_full_unstemmed | The Improved SVM Multi Objects' Identification For the Uncalibrated Visual Servoing |
| title_short | The Improved SVM Multi Objects' Identification For the Uncalibrated Visual Servoing |
| title_sort | improved svm multi objects identification for the uncalibrated visual servoing |
| topic | Micro-assembly Support vector machine Multi parts identification Broyden method Visual servoing |
| url | http://www.intechopen.com/articles/show/title/the_improved_svm_multi_objects__identification_for_the_uncalibrated_visual_servoing |
| work_keys_str_mv | AT minwang theimprovedsvmmultiobjectsidentificationfortheuncalibratedvisualservoing AT xiangjinzeng theimprovedsvmmultiobjectsidentificationfortheuncalibratedvisualservoing AT xinhanhuang theimprovedsvmmultiobjectsidentificationfortheuncalibratedvisualservoing AT minwang improvedsvmmultiobjectsidentificationfortheuncalibratedvisualservoing AT xiangjinzeng improvedsvmmultiobjectsidentificationfortheuncalibratedvisualservoing AT xinhanhuang improvedsvmmultiobjectsidentificationfortheuncalibratedvisualservoing |