Prof. Thierry Viéville
INRIA BP93 06902 Sophia
My research program is based on the assumption that for biological or artificial systems, the capabilities and performances of perceptual mechanisms are improved by the use of parameteric adaptive mechanisms.
The goal of this program is to experimentally assert this assumption, in the case of motion perception.
Recent work, beyond classical biological models of neuronal networks, consider biologically plausible multi-model estimation methods and also trajectory generation in addition to low-dimensional classifiers and cortical areas calculations in relation with the cortex project.
The goal of my project is to carry on building a strong relationship between a research team working in neurosciences of the visual perception and a research team working in artificial vision (i.e. computer vision). The long term objective is to elaborate a common theory about precise questions in both neurosciences and algorithms and their architecture in artificial vision, including computer vision applications. In the scope of this project, we consider the comparative study of visual process integration within either a biological system, i.e. the parietoventral pathways of the cortical visual system in the primate or an artificial system. Both systems deliver an estimation of the perceptual grouping and labeling of objects in the scene. Within this framework, the function and behavior of adaptive feedback mechanisms is a key point and on the leading edge of biological studies and is the problem attack here, following the core of this idea that visual processing is built around: 1) a first computational step allowing to preprocess the input information, provide initial estimates, generate hypotheses about which models to use, & 2) a refinement step using iterative mechanisms of optimization of the visual perception.
Biological vision, Motion Perception, Visual cortex, Feedback, Modelization, Simulation