In this paper,a method with an eye-in-hand configuration is developed to hit targets during visual tracking for the TLS(Tele-Light Saber) game.It is not necessary to calibrate camera parameters and predict the trajectory of the moving object.Firstly,the expression of the image Jacobian matrix for the eye-in-hand configuration is proposed,and then an update law is designed to estimate the image Jacobian online.Furthermore,a control scheme is presented and the Lyapunov method is employed to prove asymptotic convergence of image errors.No assumption for the moving objects is needed.Finally,both simulation and experimental results are shown to support the approach in this paper.
When a vehicle travels in urban areas,onboard global positioning system(GPS) signals may be obstructed by high-rise buildings and thereby cannot provide accurate positions.It is proposed to perform localization by registering ground images to a 2D building boundary map which is generated from aerial images.Multilayer feature graphs(MFG) is employed to model building facades from the ground images.MFG was reported in the previous work to facilitate the robot scene understanding in urban areas.By constructing MFG,the 2D/3D positions of features can be obtained,including line segments,ideal lines,and all primary vertical planes.Finally,a voting-based feature weighted localization method is developed based on MFGs and the 2D building boundary map.The proposed method has been implemented and validated in physical experiments.In the proposed experiments,the algorithm has achieved an overall localization accuracy of 2.2m,which is better than commercial GPS working in open environments.
A framework is presented for robustly estimating the location of a mobile robot in urban areas based on images extracted from a monocular onboard camera, given a 2D map with building outlines with neither 3D geometric information nor appearance data. The proposed method firstly reconstructs a set of vertical planes by sampling and clustering vertical lines from the image with random sample consensus (RANSAC), using the derived 1D homographies to inform the planar model. Then, an optimal autonomous localization algorithm based on the 2D building boundary map is proposed. The physical experiments are carried out to validate the robustness and accuracy of our localization approach.
In this paper,a method combining perspective-n-point(PnP) and novel iteration algorithm is developed to measure the pose of a target in high precision for Tele-LightSaber game.The PnP algorithm is used to obtain a rough pose,which is taken as the initial value of the iteration algorithm.The iteration algorithm utilizes the unit quaternions to represent the rotations.Then the result is optimized with Kalman filter.Considering the real-time and accuracy of the pose measurement,a fast feature extraction algorithm including object location,edge detection and corner detection is adopted to get the corners in high precision.The experiments and results verify the effectiveness of the proposed method.