TERRANUMERICA

My current research is developed in the framework of Cap Digital Business Cluster TerraNumerica project. This project aims to develop a production and exploitation platform, by allowing the definition and visualization of synthetic urban environments. The platform aims to increase the productivity and the realism of urban modeling.

Main tasks:
  • Fusion and filtering data (Aerial and Facade Images, LIDAR Data of Vehicle and Fixed systems.)
  • Reconstruction and semantic extraction
Some Results: CMM Contribution. Morphological image analysis for urban modeling.


Human-Machine interface based on the movement of the lips for robotics systems on surgery

In this project, we have introduced a novel method for real--time lip segmentation and feature extraction in video sequences, applied to human--machine interfaces for robot command and manipulation. The method uses a set of different pixel--based segmentation algorithms and morphological restrictions in order to extract the mouth area from the frames. A fuzzy inference system was used in order to produce a small subset of discriminate features for gesture classification. A state machine was used to control the operation workflow of the system and the robot command. Experimental results have shown that the method is both robust against difficult conditions (uncontrolled lighting and bearded individuals) and fast.

Numerical modeling of free surfaces form and texture mapping

MultiView

Development of classification algorithms for coffee beans employing techniques of computer vision

This project was mainly based on neural networks and support vector machine (SVM) design and implementation on programmable logic device (PLD). In addition, we present the implementation of IEEE 754 standard for representing numbers of floating point. The architecture implementing the system is described in detail and mapped on a developed system whit field programmable gate array - FPGA .