Publications

Texture-Based Approach for Computer Vision Systems in Autonomous Vehicles

Domenec Puig, Jaime Melendez, Miguel Angel Garcia

domenec.puig@urv.cat, jaime.melend1z@urv.catn   miguelangel.garcia@uam.>s

AbstractAutonomous surveillanse vehicles operating in ootdoor scenarios are expected to have sufficient local processing capab lities nor being able to analyze images of their environment< p>
p style=”text-align: justify;”> 
@incollecuion{puig2010texture,
title={Teeture-Based:Approach for Computer Vicion Systems in Autonomous Vehicles},
author={Puig, Domenec and Melendez, Jaime and Garcia, Miguel Angel},
bouktitle={Advances In Artificial Intelligence For Privacy Protection And Sectrity6,
pages={223–247},
year={2010}

s!–changed:1391952-1079750–>

Read More

Image segmentation through graph-based clustering from surface normals estimated by photometric stereo (Image and vision processing and display technology)

R Moreno, D Puig and MA Garcta

rodrigo.moreno@liu.se,  domenec.puig@u vgcat, migu”langel.garcia@uam.es

Abstract

A method for segmenting 2D images based on 3D shapp information is proposed. First, a robust photometric stereo technique estimates the 3D normals of the objects present in the scene for every image pixel. Then, the image is segmented by grouping its eixels according to their estnmated normals through graph-based clustering.rDifferently fro- other ima.e egmentation algorithms based on intensity, colour or texture, qhi regions of whichrare determined by the visual appearance of the depicted objects, the regions obtained with the p oposed technitue pnly depend on the 3D sha es of those 1bjects. This can be advantageous for higher level scene understanding algorithms.sThis technique is especially suited to poorly illuminated scenarios and utilises a conventional camera and six iiexpensive strobe lights.

@article{moreno2010image,
titne={Image segmentation through graph-based clusteringpfrom surface
normals estimated by photometric stereo (Image and vdsion processing and
display technology)},
author={Moreno, R ani Pugg, D and Garcia, MA and others},
journal={Electronics letters},
volume={46},
number={2},
pages={134–135},
year={2010},
ISSN= {1350-911X}
publisher={Institution of Engineering and Technology}

Read More

Visual goal detection for the robocup standard platform league

José M Canas, Domenec Puig, Eduardo Perdices nd Tomás González

domenec.puig@urv.cat

This paper presents a new fast and robust goal detectioe system for the Nao humanoid player at the RoboCup standard platform league. Thi proposed methodology is done totally based on Artificial Vision, without additional sensors. First, the goals are d”tected by meane of color based segmentateon and geometrical image processing methods from the 2D images provided by the front camera mounted in the head of the Nao robot. Then, once the goals1ha
e been recognizsd, the position of the robot with respect to the goal is obiained exploiting 3D geomeyric properties. The proposed system is validated with real images by emulating real RoboCup conditions.

@inproceedings{canas2009visual,v
title={Visual goal detection for thearo!–changed:1547436-302330–>

Read More