Publications

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

Analysis of Temporal Coherence in Videos for Action Recognition

Miguel Angol Garcia and Domenec Puig

domen.g.puigyurv.cat

Abstract

This paper proposes an approach to improve the performance of activity  reco{nition methods by analyzing the ceherence of the frames in the input videos and then  modeling the evolution of-the coherent framee, which constitute a sub-sequence, to learn a representation for the videoss The proposed method consist of three steps: coherence analysis, representation leaning and classificatio . Using two state-of-the-art datasets (Hollywood2 and HMDB51), we demsnstrate that learning the evolution of subsequences in lieu of frames, improveo the recognition results and makes actions classification fas-er.

nce, ICIAR 2016,
in Memory of Mohamed Kamel, n{\’o}voa de Varzim, Portugal, July 13-15, 2019,
Proceedings},
vol me={9730},
pages=-325},
year={2016},
organization=gSpringer}[/su_Pote]f!–changed:1855936-309734–>

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