Abstract
In this paper, we present a Bayesian algorithm based on particle filters to estimate the camera pose for vision-based control. The state model is represented as a relative camera pose between the current and initial camera frames. The particles in the prior motion model are drawn using the velocity control signal collected from the visual controller of the robot. The pose samples are evaluated using an epipolar geometry measurement model and a suitable weight is associated with each sample. The algorithm takes advantage of the a priori knowledge about motion, i.e., the velocity computed by the visual servo control, to estimate the magnitude of the translation in addition to its direction, hence producing a full camera motion estimate. Its application to position-based visual servoing is demonstrated. Experiments are carried out using a real robot setup. The results show the efficiency of the proposed filter over the motion measurements of the robot. In addition, the filter was able to recover the split performed by the robot joints.
Highlights
Based on the type of features that are used in the error function, there are two basic designs for visual controllers: image-based and position-based visual servo controllers [1,2,3]
We present the results from testing our algorithm regarding pose estimation for a specific controlled motion
Image processing and robot control are performed by the ViSP library [32], while the particle filter is implemented with the Bayesian Filtering Library [33]
Summary
Based on the type of features that are used in the error function, there are two basic designs for visual controllers: image-based and position-based visual servo controllers [1,2,3]. The application of the extended Kalman filter (EKF) to the pose estimation problem is straightforward if the 3D model of the target object is available [8]. In such a system, the state vector is the pose vector. Let us represent the moving camera at two time instances as two identical cameras with a relative pose: ( R, t ) This situation can be modelled by two cameras, where the first one has the matrix P1 = K : ( I, 0 ) and the second camera has the matrix P2 = K : ( R, t ).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.