Abstract
This article considers the fundamental task of 3-D tracking as a direct image registration problem. 3-D tracking consists in continuously recovering the camera motion in the Euclidean space. Direct methods refer to those that exploit the pixel intensities without intermediate steps, e.g., no extraction of image features. This work presents new photogeometric transformation models and nonlinear optimization methods for directly registering calibrated central omnidirectional images of planar objects. The proposed approach simultaneously reconstructs the camera motion, the planar structure, and the illumination variations so as to perform the tracking. Experimental results show that 3-D tracking can indeed be highly robust and accurate even for this type of vision systems.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Journal of Control, Automation and Electrical Systems
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.