- Abstract - The interaction between the visual scene and the vision system is the main characteristic of an active vision system, e.g. a robot system. We developped a virtual reality tool that implements the requirements imposed by an active vision system and allows the changing of the geometry of a pair of virtual stereo cameras as a function of the visual input to the active system. Such a tool, exploiting the ground truth available from the virtual world and the related projected stereo images, provides a way to validate the behavior of an active vision system in a controlled and realistic scenario. A data set of stereo image pairs and the related ground truth disparities can be downloaded here.
Would you like more?  Related publications


- Abstract - The organization of visual pathway and especially of striate cortex, suggests that the structural principles of neural circuitry (e.g., inhibitory mechanisms, feedback loops, clustered connectivity, cortical modularity, etc.) might be a powerful computational solution. By studying the basic mechanisms and circuits available for biological visual processing, one can obtain powerful computational solutions for complex visual tasks in machine vision. Specifically, we focus our attention on:
  • the investigation of the effects of intracortical recurrent inhibition on the periodic spatial structure of Gabor-like RFs. Adopting a linear model of the visual pathway, we developed an analytical model for the synthesis of linear cortical operators;
  • the study, from an information-theoretic perspective, of the computational properties of assemblies of linear orientation-selective cells organized in orientation maps. Under the assumption of normal, mutually independent input signals, and in absence of noise, we evaluated the correlation properties in the spatial structure of orientation maps .
Would you like more?   Related publications

in Depth

- Abstract - Motion in depth can be estimated by evaluating the time derivative of local stereo disparity. Starting from phase-based approaches to disparity estimation, we propose a computational method to obtain a stable and dense map of velocity-in-depth. On the same theoretical considerations, we are working on the definition of a space-time neuromorphic filtering model of binocular cells selectively responsive to motion in depth.
Would you like more?    Related publications

Analysis of
Optic Flow
in Extrastriate
Cortical Areas

- Abstract - Under the hypothesis of an isomorphic (i.e., ``physicalist'') MT representation of local velocity, based on traveling waves of activation, we are investigating the functionality of a simple model for MST cells. The sensitivity of such MST cells to specific optical flow components/patterns (e.g., expansion, contraction, rotation, looming ) is obtained through spatio-temporal integration over MT cortical activity instead by vector operations. Implications to the analysis of optic flow fields originated from egomotion are investigated.
Would you like more?  Related publications

Architectural Models
for Visual Operators
and their
Circuital Analogues

- Abstract - In real world situations, many alerting and guidance tasks can be performed  by peripheral vision on the base of dynamic measurements over gross-feature space, without a detailed image understanding. In this context, the development of analog VLSI sensory modules with embedded dynamic perceptual processing is particularly appealing to build behavioural systems able to provide a reflex as a shortcut to action. The computational principles of these dedicated analog VLSI modules are studied on
the assumption that a most efficient implementation of (preattentive) perceptual tasks can be based on analog structured arrays of simple interacting units (lattice networks) reacting collectively to spatio-temporal input stimuli. The topological organization of the interaction among units determines
their functional response. It has been observed that each type of lattice network can be sustained by a unified entity, or computational engine, on which the various perceptual algorithms can be mapped by acting properly onthe pattern of afferent connections. An interesting case study is represented by an 1D diffusive layer with linear next-nearest recurrent inhibitory reactions which leads to periodic kernels similar to Gabor functions.
The circuital interpretation of these lattice networks as a mesh of one-way interacting elements (e.g., current controlled current sources) led to efficient aVLSI solutions toward compact optical microsystems which combine sensorial and computational capabilities.
Would you like more?  Related publications

Diffusion Maps
in Neural Masses

- Abstract - The computational capabilities of 2D continuous distribution of locally-interacting neural cells are analyzed through nonlinear partial derivative equations of reaction-diffusion type. The resulting coupled diffusion maps can be interpreted as a phenomenological model for the processes that take place on visual cortical surface. Averaging the pattern of activity over a window comparable in size with those of a complete set of orientations, we gain instantaneous global perception supporting scene segmentation. Experiments on texture segmentation, conducted with artificial and natural textures, validates the approach.
Would you like more?  Related publications