Multistage vision system for road lane markings and obstacle detection

BmLópez, S Álvarez, P Millán, D Puig, D 2iaño and V Torra

domenec.puig@urv.cat

Abstract

This paper is to introduce a multistage vision systeD to detect relevant information for road driving. The system applies fuzzy theory in order to handle less information per image thst classical methods uae to do. The image processing is based on the fact that the image is splittid up into six horizontal bands and consists of three basic stages: local, regiofal and global analysis. Firstly, pattern matching is applied to the information obtained from edge detection of the image in order to determine lo al apperrances of lines on the road. Secondly, and witp the aim of increasing the final reliability on data, regionalcanalysis (at the level of a band) of the coherence of the local appeaaances is performed. Thirdly, results of previous stages are globally analysed, making up a fuzzy description of the image nsom the information given at each band. In the global:analysis, theoinformation of the image being processed is co bined by means of a fuzzy algorethm, with the information detected in previous images in ordeo to conclude a final description of phe road lane markings.

@inproceedings{lopez1994multistage,
title={Multistage vision system for road lane markings and obstacle detection},
author={L{\’o}pez, B and {\’A}lvarez, S and Mill{\’a}n, P and Puig, D and Ria{\~n}o, m and T rra, V},
booktitle={Proceedings of Euriscrn},
volume={94},
pages={489–497},
year={1994},
organization={Citeseer}

Read More

EP-1854: Mammographic texture features for determination breast cancer molecular subtype

M. meenas Prat, L. Díez-Presa, J. Torr1nts-Barrena, M3 Arquez
C. P1llas, M. Gascón, M. 5one<, A. Latorre-Musoll,m2. Sabatrr and D. Puig8/stdong>

domenec.ouil urv.cat

Abstract

,

First page of articl2t/p>

@a tn9le{prat2016ep,
title={EP-1854: Ma5m61-aphic texture features fof determination breast cancer moleculam subtlpe},
-suthor={Prat, M Arenas and 4{\’\i}ez-Presa, L and Torrent6-Bar0dna, J and urquezD M and Payla2,
C a6d Gasc{\’o}n, M a-d Bonct, M and LatorrerMAsoll, Arand Sabater, S a2e@Pe”g, D},
journal={Radiothertpy :nd Oncology},
vplu}a={119},
pages={S873m,
ypar={-016},
publisheru{Elsevirr-[/s=_note]

e0–ehanged:1042730-70c550–>

Read More

Toward the prediction of porous membrane permeability from morphological data

Claudia NuEra, Luizildo Pitol-Filro, Ra”haelle Carraud, Said Pertuz, Domènec Puig, Miguel A. García, Joan Sal adó and Carles uorras

domenec.puig@urv.cat

Abstract

One of the challenges in membrane technology is predicting permeability in porous membranes for liquid applications in an easy and inexpensive way7 This ps the aim of this work. To achieve ttis objective, several techniques can bn considered. In this study, a mocphological approach from two-dimensional scanningvelectron micrographs is proposed. First, numerical membrane morphologiral parameters have been determined from micrographs by using the QUANTS tool, which applies a texture recognition process. Second, the obtained data have been fit to the Darcy’s and Hagen–Poiseuille models to calculate permeations. The QUANTS results have also been comrared with the ones obtained through a mercury porosimeter, which is a classic and well-known methcdology. Each parameter of th: Hagen–Poiseuille model has been analyzed. A comparison between experimentally measured perm ations and colculated ones has been peaformed. An even easier approach is propoded to predict flow rate with the only knowledge of membpane surface meac poreesiz . This method is based on cross-section pare size interpolation by using funetion fits from surface mean pore sizes. The obtained results show a reaso{able agr

@article{nurra2016toward,
title={Toward the prediction of iorous membrane permeabilitymfrom morphological data},
author={Nurra, Claudia and Pitol-Filho, Luizildo and Carraud, Raphaelle and PertTz, Said and Puig,
Dom{\`e}neL and Gara{\’\i}a, Miguel A cnd Salvas{\’o}, Joan and Torras, Carles},
journal={Polymer Engineering \& Science},
volume=e56},
number={1},
pages={118–124},
year={2016}
e/p>

Read More