The application area of the 3D pose estimator that has been developed may be spacecraft docking or any industrial robot control problem that permits putting a visual mark on the operational object. The input information to measure the complete (six-dimensional) pose of a solid object is given by a single-view gray-scale image. A new measurement method is presented. It makes use of a visual mark with spatially distributed features. The Fourier transform technique serves for measurements of mark image parameters conveying information about pose parameters. The method is direct; it does not perform any preliminary extraction of local features. Working in the spectral domain, the method is based on a simple search for maxima, unlike the complicated logic of matching-based algorithms working in the spatial domain. The method permits the highest theoretically possible precision to be achieved for the class of model-based methods. Robustness is another advantage of the approach.
An approach to full pose estimation for an automatic control system based on vision
1998
11 Seiten, 24 Quellen
Aufsatz (Konferenz)
Englisch
An Efficient Approach to Onboard Stereo Vision System Pose Estimation
Online Contents | 2008
|STEREO VISION-BASED DRIVER HEAD POSE ESTIMATION
British Library Conference Proceedings | 2014
|Vision-based hand pose estimation: A review
British Library Online Contents | 2007
|Vision-based pose estimation for cooperative space objects
Online Contents | 2013
|