A Vision-Based System for Object Identification and Information Retrieval in a Smart Home

 This is some older work carried out during the beginning of the PhD:

The paper describes a hand held device developed to assist
people to locate objects and retrieve information about the object in a
home. The system developed is a standalone device to assist persons with
memory impairments such as people suffering from Alzheimer’s disease.
A second application is object detection and localization for a mobile
robot operating in an ambient assisted living environment. The device
relies on computer vision techniques to locate a tagged object situated in
the environment. The tag is a 2D color printed pattern with a detection
range and a field of view such that the user may point from a distance
of over 1 meter.

Video is also available on youtube:
http://youtu.be/0M-_rwKvD3E

Installation of OpenCV 2.4 on Ubuntu 12.04

This link seems to contain the right instructions on how to successfully install OpenCV in Ubuntu.

http://code.google.com/p/qt-opencv-multithreaded/wiki/Documentation

Visual Memories

We are currently developing a real-time method that automatically creates a visual memory of a scene using the growing neural gas (GNG) algorithm. The memory consists of a graph where nodes encode the visual information of a video stream as a limited set of representative images. GNG Nodes are automatically generated and dynamically clustered. This method could be employed by robotic platforms in exploratory and rescue missions.


Accepted for publication in IET Electronics Letters(April 2012)

My First Blog

I'm currently working on getting a team of robots to memorize what they see....