The Improved SVM Multi Objects's Identification for the Uncalibrated Visual Servoing
Authors:
Open Access
- 1 January 2009
- journal article
- research article
- Published by SAGE Publications in International Journal of Advanced Robotic Systems
- Vol. 6 (1)
Abstract
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.Keywords
This publication has 10 references indexed in Scilit:
- Fuzzy-Rough Sets Assisted Attribute SelectionIEEE Transactions on Fuzzy Systems, 2007
- Consideration of illumination effects and optimization of window size for accurate calculation of depth map for 3D shape recoveryPattern Recognition, 2007
- Task-Independent Robotic Uncalibrated Hand-Eye Coordination Based on the Extended State ObserverIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2004
- Uncalibrated Dynamic Visual ServoingIEEE Transactions on Robotics and Automation, 2004
- Visual Servoing Invariant to Changes in Camera-Intrinsic ParametersIEEE Transactions on Robotics and Automation, 2004
- Support Vector Method for RobustARMA System IdentificationIEEE Transactions on Signal Processing, 2004
- LDA/SVM driven nearest neighbor classificationIEEE Transactions on Neural Networks, 2003
- Asymptotic trajectory tracking of manipulators using uncalibrated visual feedbackIEEE/ASME Transactions on Mechatronics, 2003
- A dynamic quasi-Newton method for uncalibrated visual servoing2003
- Visual pattern recognition by moment invariantsIRE Transactions on Information Theory, 1962