Visual Servoing in Unconventional Environments

Most robotic vision algorithms are proposed by envisaging robots operating in structured environments where the world is assumed to be rigid. These algorithms fail to provide optimum behavior when the robot has to be controlled with respect to active non-rigid targets. This work presents a new framework for visual servoing that accomplishes the robot positioning task even in non-rigid environments. We introduce a space-time representation scheme for modeling the deformations of a non-rigid object and propose a model-free hybrid approach that exploits the two-view geometry induced by the space-time features to perform the servoing task. Our formulation can address a variety of non-rigid motions and can tackle large camera displacements without being affected by the degeneracies in the task space. Experimental results validate our approach and demonstrate the robust and stable behavior.


"Visual Servoing in Non-Rigid Environments: A Space-Time Approach"
Santosh K. Divvala, C. V. Jawahar
International Conference on Robotics and Automation (ICRA) 2007 (Oral Presentation)
[Paper] [Presentation]

"Robust Homography-based Control for Camera Positioning in Piecewise Planar Environments"
Santosh K. Divvala, C. V. Jawahar
Indian Conferece on Computer Vision, Graphics & Image Processing (ICVGIP), 2006
[Paper] [Poster]

"Visual Servoing in presence of Non-Rigid Motion"
Santosh K. Divvala, C. V. Jawahar
International Conference on Pattern Recognition (ICPR) 2006
[Paper] [Poster]


"Visual Servoing in Unconventional Environments"
Santosh K. Divvala
Undergraduate Thesis
Center for Visual Information Technology, IIIT-Hyderbad, July 2006.

"Non-Rigid Motion Canceling"
Santosh K. Divvala, C. V. Jawahar
Technical Report