I will defend my PhD on the 17th of March 2015.
Our improved Modelling Scheme to accomodate spatial weights in photometric moments has been accepted in ICRA2015 to be held in Seattle, USA.
Jan 12, 2014
Our work on tunable visual features has been accepted in ICRA2014 to be held at HongKong. The camera-ready version and video are available below.
I commenced my PhD in Computer Science in October 2011 under
the supervision of Dr.François Chaumette in the LAGADIC
team at INRIA Rennes. My doctoral research is being funded by an INRIA grant.
I graduated with a Masters-by-Research degree in Robotics from Ecole Centrale de Nantes in 2010. In fact, I had completed a dual Erasmus Mundus Masters program called EMARO. Under this program,I spent the first year at Warsaw University of Technology, from where I received a Masters degree, also in Robotics and Control.
I am broadly interested in the following areas:
My PhD is aims to develop methods to best utilize the rich intensity information available in the image for Visual Servoing. My current efforts are focussed on using photometric moments for visual servoing and practical issues surrounding this theme.
We propose a new type of visual features for visual servoing : photometric moments. These global features do not require any segmentation, matching or tracking steps. The analytical form of the interaction matrix is developed in closed form for these features. Results from experiments carried out with photometric moments have been presented. The results validate our modelling and the control scheme. They perform well for large camera displacements and are endowed with a large convergence domain. From the properties exhibited, photometric moments hold promise as better candidates for IBVS over currently existing geometric and pure luminance features.
we introduce the concept of tunable visual features for moments based visual servoing schemes. The main contribution of this work is the introduction of tunable shift points along with some effective methods to tune them. We propose two different metrics: the first metric ensures optimal response of the control to errors in the image space and the second metric ensures orthogonality between the interaction matrix components (vectors) related to the control of x and y rotational motions. With the proposed method, it is possible to design moment invariants-based visual features whose interaction matrix is always non-singular for any desired pose (parallel or non-parallel). Thus, this work makes a significant contribution to the difficult problem of controlling the rotational motions around the x and y axes, when all the 6dof are involved. Two case studies are presented to demonstrate the validity of the proposed ideas. Results from each case are then used to design a moment invariants-based visual feature. This visual feature is used for visual servoing with a symmetrical object using binary moments.
In this work, we dealt with the problem of exogenous image regions appearing and leaving the field of view during the visual servoing.
Complete list (with postscript or pdf files if available)