Design and Implementation of Visual Servoing System for Realistic Air Target Tracking

• Main Authors: YAU WEI GUAN, 丘偉源
• Other Authors: Li-Chen Fu
• Format: Others
• Language: en_US
• Published: 2000
• Online Access: http://ndltd.ncl.edu.tw/handle/90434641362449541164

碩士 === 國立臺灣大學 === 電機工程學研究所 === 88 === In this thesis, a real-time visual tracking system based on our proposed motion estimation algorithms is developed. The proposed motion estimation algorithms are used to predict the location of target and then to generate a feasible control input so as to keep the target stationary in the center of image. The work differs from the previous algorithm of motion estimation in that it is capable to decouple the estimation of motion from the estimation of structure. The weak perspective projection is used to solve this problem. We use our proposed target detection methods for the computation of optical flow. These image displacements are fed to motion estimation algorithms so as to generate an appropriate camera motion that achieve tracking. The major contribution of this work is that simple, none computation intensive, correspondence-free, and numerically stable 3D motion estimation algorithms are derived. The robust target detection method in simple environment and a time reduction of SSD method in complex environment is somewhat minor contribution. The visual tracking system is accomplished at a rate of 30 Hz. The robustness of the visual tracking system based on the proposed motion estimation algorithms has been validated by a number of experiments.