Research On Visual Location And Target Tracking Of Wheeled Mobile Robot

For Wheeled Mobile Robot(WMR), acquiring information by vision is one of the most important sensing methods.The question to locate and track the moving target of WMR based on monocular image sequence is studied in detail.A real-time video sequence capturing and data processing system of WMR based on VFW is designed and implemented in Delphi 6. The method of obtaining and tracking target characteristics is studied. The vision localization and target tracking system of WMR is schemed and accomplished. Then 2D characteristics in image space are acquired, such as position of target centroid.In order to acquire 3D spatial position and motion parameters of moving target, the limitation of second focus method to get the depth of target is analyzed according to perspective projection model of target centroid. Then, the constraint for obtaining 3D position and motion parameters of moving target centroid from monocular image sequence is presented and proved in this paper. With this constraint, a nonlinear Extended Kalman Filter algorithm for estimating 3D spatial position and motion parameters of moving target centroid from monocular image sequence is proposed. The simulation results show that the proposed method is effective and recommendable. For image sequence estimating motion parameters, the information can be used to the extent. Therefore, the estimation results are more accurate. Meanwhile, the Recursive Kalman Filter employed, much memory space and calculation time are spared during the estimation process.How to realize the serial communication between computer and microcontroller by SPComm component is discussed to transfer the data results of target recognition to decision and control system.